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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104209
    Prev
    Next
    INDEX
    Explanations

    enteric

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

    words ending in "ic", particularly in scientific and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    I
    -3.61
    on
    -3.41
    *
    -3.00
    на
    -2.88
     Significantly
    -2.81
     Various
    -2.81
    <em>
    -2.77
    𐄁
    -2.77
     Sufficient
    -2.70
    ?
    -2.66
    POSITIVE LOGITS
    ic
    3.09
    颙
    2.67
    ⌵
    2.64
    ؟
    2.63
    矬
    2.58
    锖
    2.52
    的
    2.52
    冧
    2.48
    gliche
    2.45
    后者
    2.44
    Activations Density 0.030%

    No Known Activations