© 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. 57505
    Prev
    Next
    INDEX
    Explanations

    authorized by copy

    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
     Franklin
    -0.77
    Franklin
    -0.71
     powerful
    -0.71
    obraz
    -0.70
    joseph
    -0.69
     λα
    -0.69
    ntry
    -0.68
     Internal
    -0.68
     stillness
    -0.68
    getSelectedItem
    -0.68
    POSITIVE LOGITS
    รม
    0.77
     ((((
    0.74
     laughs
    0.72
     unbiased
    0.70
     OneDrive
    0.69
    zkod
    0.69
     Iroquois
    0.68
    owali
    0.68
     CUCET
    0.68
    Championship
    0.68
    Activations Density 0.042%

    No Known Activations