© 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. 115680
    Prev
    Next
    INDEX
    Explanations

    Winchester, ESPN Innovates

    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
     Й
    -0.87
    などを
    -0.81
    🔺
    -0.79
    icidio
    -0.78
     möjligt
    -0.77
    Akan
    -0.77
     ş
    -0.76
     रा
    -0.76
     algebraic
    -0.75
     <<"
    -0.75
    POSITIVE LOGITS
    AtIndexPath
    0.96
     Enquanto
    0.84
     vertreten
    0.82
    锈
    0.82
     Qualquer
    0.79
     qualche
    0.77
    ソッド
    0.76
    咬
    0.75
     esigen
    0.74
    所属
    0.74
    Activations Density 0.003%

    No Known Activations