© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108387
    Prev
    Next
    INDEX
    Explanations

    generated document annotations

    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
    deras
    -1.02
     arrend
    -0.86
    abung
    -0.85
    média
    -0.85
    لاة
    -0.85
     terrible
    -0.85
    挽回
    -0.84
     paiement
    -0.84
     rodeado
    -0.82
    💀
    -0.82
    POSITIVE LOGITS
     NOT
    1.16
    not
    1.00
     не
    0.97
    NOT
    0.95
     ardent
    0.94
     полностью
    0.92
     completamente
    0.91
    你們
    0.86
     नहीं
    0.82
     不是
    0.81
    Activations Density 0.003%

    No Known Activations