© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    Max activating token followed by specific tokens

    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
    🩺
    -0.87
     stung
    -0.85
     nightly
    -0.77
     Skyline
    -0.76
    ﷲ
    -0.71
    ◈
    -0.71
    鿬
    -0.71
    Bitcoin
    -0.71
     BlackBerry
    -0.70
    ignée
    -0.69
    POSITIVE LOGITS
     Checklist
    0.93
     Huston
    0.83
    Checklist
    0.81
    glyph
    0.80
     Procedures
    0.80
     Clients
    0.79
    REQUEST
    0.78
     clients
    0.77
    licite
    0.74
     slumped
    0.74
    Activations Density 0.006%

    No Known Activations