© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14667
    Prev
    Next
    INDEX
    Explanations

    adaptation

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

    This neuron strongly activates on numeric tokens—especially multi‐digit or decimal numbers.

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

    extremely high numerical values (over 1000) appearing in technical or formal text contexts.

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

    high-frequency function words (stopwords) such as determiners, prepositions, conjunctions, and quantifiers.

    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
    ত
    0.76
    
    0.75
     セミ
    0.73
    INSON
    0.71
     상당히
    0.71
     setores
    0.71
     специалисты
    0.70
     Noronha
    0.70
    сть
    0.67
    штейн
    0.67
    POSITIVE LOGITS
    n
    1.02
    3
    0.86
    gel
    0.80
    2
    0.79
    yrs
    0.77
    ’
    0.77
    naz
    0.76
    8
    0.75
    9
    0.75
    whitespace
    0.74
    Activations Density 0.000%

    No Known Activations