© 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. 93384
    Prev
    Next
    INDEX
    Explanations

    locations, questions, and specific phrases

    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
    emptory
    -0.93
     Kette
    -0.78
     disposer
    -0.73
     EVOLUTION
    -0.73
    ステム
    -0.73
    ależy
    -0.73
     smoked
    -0.73
     kiel
    -0.72
    Alu
    -0.71
     економі
    -0.71
    POSITIVE LOGITS
     Moh
    0.91
    طلاق
    0.79
     deprive
    0.77
    giz
    0.73
    scsi
    0.73
     arrive
    0.71
     quiser
    0.71
    cstr
    0.69
    npm
    0.69
     Wah
    0.68
    Activations Density 0.023%

    No Known Activations