© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110787
    Prev
    Next
    INDEX
    Explanations

    GPL, Catherine, ID, UIView, Institute, High, Multi, slides, function

    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_34/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
    鮠
    -1.45
    ꯵
    -1.42
     pneu
    -1.40
    スポンサーリンク
    -1.38
    Semua
    -1.38
    crocs
    -1.32
    Répondre
    -1.31
    さてさて
    -1.30
    angkap
    -1.30
    بوابة
    -1.30
    POSITIVE LOGITS
    '
    1.73
    ...
    1.59
    a
    1.54
    ha
    1.51
    e
    1.48
    </strong>
    1.47
    y
    1.47
    Y
    1.46
    s
    1.43
    al
    1.40
    Activations Density 0.491%

    No Known Activations