© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5628
    Prev
    Next
    INDEX
    Explanations

    properly authenticating

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized in detecting floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words ending in common suffixes like "-ian", "-tion", or "-ology" in academic or formal text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal, scholarly or legal-text markers, especially citation-style elements and abstract technical nouns (including hyphenated constructions) common in references and institutional statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    血糖
    0.64
    िकास
    0.62
    ře
    0.62
     hyperglycemia
    0.60
    gluc
    0.59
    स्टेंस
    0.58
    appcompat
    0.57
     औसत
    0.57
    botones
    0.57
    phenoxymethyl
    0.57
    POSITIVE LOGITS
    ?
    0.88
    !
    0.84
    ?”,
    0.75
     тощо
    0.74
    !",
    0.70
    !;
    0.70
    ?",
    0.69
    ?");
    0.67
    ?”
    0.66
     etc
    0.65
    Activations Density 0.000%

    No Known Activations