© 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. 34-GEMMASCOPE-RES-131K
    7. 38443
    Prev
    Next
    INDEX
    Explanations

    html attributes and code tags

    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
     in
    -1.87
     even
    -1.80
     just
    -1.75
    <bos>
    -1.70
    を
    -1.70
    というわけで
    -1.63
    があります
    -1.60
     epitom
    -1.58
     as
    -1.53
     at
    -1.52
    POSITIVE LOGITS
    為に
    1.94
    ところに
    1.77
    
    1.70
    様な
    1.67
    扨
    1.67
    へ向
    1.65
    の準備
    1.63
    際は
    1.61
    の方に
    1.60
    んですよ
    1.59
    Activations Density 0.076%

    No Known Activations