Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 236
    Prev
    Next
    INDEX
    Explanations

    clothing and bedding

    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_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
    </sup>
    -1.82
     devenus
    -1.62
    ⡪
    -1.56
    敺
    -1.52
     quelques
    -1.46
    O
    -1.46
    }{
    -1.44
     Slight
    -1.41
     KPIs
    -1.41
    
    -1.41
    POSITIVE LOGITS
     our
    1.66
    いる
    1.49
     from
    1.49
     EVERY
    1.48
    城的
    1.42
     этому
    1.41
     Richard
    1.39
     acondicionado
    1.39
    遗憾
    1.37
    しているので
    1.34
    Activations Density 0.010%

    No Known Activations