© 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. 50189
    Prev
    Next
    INDEX
    Explanations

    code exports

    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
     ulica
    -0.86
    呼ば
    -0.85
    去的
    -0.83
    わけで
    -0.80
     transferred
    -0.79
     gwaran
    -0.78
     yalnız
    -0.78
    ぅ
    -0.78
     demand
    -0.77
     transported
    -0.77
    POSITIVE LOGITS
     the
    1.35
    const
    1.10
    การ
    1.06
    LITE
    0.93
    seln
    0.92
    newcommand
    0.90
     menit
    0.88
    getBoolean
    0.84
    \}$.
    0.84
    函数
    0.84
    Activations Density 0.011%

    No Known Activations