© 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. 86949
    Prev
    Next
    INDEX
    Explanations

    words following specific prefixes

    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
     this
    -1.31
     just
    -1.18
     or
    -1.02
    )//
    -0.98
    ָה
    -0.96
     tats
    -0.94
    至此
    -0.94
    kungen
    -0.92
    =((
    -0.92
     at
    -0.91
    POSITIVE LOGITS
    μών
    1.04
     begrenzt
    0.97
    観て
    0.96
    ୬
    0.95
    翃
    0.94
    
    0.93
     более
    0.91
     dépasser
    0.91
     😊
    0.91
    坶
    0.90
    Activations Density 0.004%

    No Known Activations