© 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. 22-GEMMASCOPE-RES-131K
    7. 39786
    Prev
    Next
    INDEX
    Explanations

    technical component substrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    にほんブログ村
    -1.73
    に戻る
    -1.52
    に入れ
    -1.48
    に行って
    -1.46
    länd
    -1.45
     vermelhas
    -1.44
     lentejuelas
    -1.43
    さあ
    -1.42
    nowy
    -1.40
     fábricas
    -1.40
    POSITIVE LOGITS
    u
    1.85
    は
    1.71
    があり
    1.63
    などが
    1.62
    ですが
    1.58
    <bos>
    1.57
    i
    1.56
    o
    1.51
    と
    1.51
    om
    1.48
    Activations Density 0.023%

    No Known Activations