© 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. 2199
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    The neuron specifically detects numeric tokens containing decimal points (floating‐point numbers).

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

    DOI identifiers and numerical citation references in academic or technical documents.

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

    emphatic or focal words in descriptive or header-like passages, especially determiners and nouns that introduce sections or convey totality/completeness.

    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
    Weitere
    0.77
    Ő
    0.73
    )}{
    0.71
    Sierra
    0.71
    
    0.70
    Би
    0.68
    Основные
    0.68
    L
    0.67
    Č
    0.66
    Biographie
    0.66
    POSITIVE LOGITS
    いた
    1.02
     ilegal
    0.90
    न
    0.90
    ваме
    0.89
     analiz
    0.86
     kontrak
    0.86
     മാന
    0.86
     olok
    0.85
     siglo
    0.84
     sert
    0.84
    Activations Density 0.000%

    No Known Activations