© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4199
    Prev
    Next
    INDEX
    Explanations

    cited as, listed for, release includes

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

    The neuron fires on numeric tokens (including integers, decimals, percentages, etc.).

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

    prepositions, particularly "of", in contexts involving lists, measurements, or technical specifications.

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

    domain-specific technical or scientific terms, especially jargon related to engineering, medicine, or measurements.

    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_24_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
    Puedes
    0.80
     योर
    0.80
    izoen
    0.79
    izieren
    0.79
     거라고
    0.77
     인간
    0.76
    Ciudad
    0.76
     őket
    0.75
     너
    0.74
    🌎
    0.74
    POSITIVE LOGITS
     tumour
    0.94
     valve
    0.94
     criteria
    0.89
     criterion
    0.84
     abnormalities
    0.83
     sarcoma
    0.83
     measles
    0.82
     indicator
    0.82
     pathogenicity
    0.82
     syndrome
    0.81
    Activations Density 0.229%

    No Known Activations