© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63110
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     wherein
    -0.96
     skall
    -0.95
     which
    -0.93
     folks
    -0.88
     сочи
    -0.86
     полиции
    -0.84
    听见
    -0.83
    ⇐
    -0.83
    wherein
    -0.82
     however
    -0.81
    POSITIVE LOGITS
     nhàng
    0.94
     loại
    0.85
    》（
    0.85
    semb
    0.84
    %">
    0.82
    <em>
    0.81
    upaten
    0.81
     storylines
    0.81
    iação
    0.81
    dientemente
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.