© 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. 22-GEMMASCOPE-RES-131K
    7. 130220
    Prev
    Next
    INDEX
    Explanations

    identifier or column names

    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_22/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
     význam
    -1.00
    GeoNames
    -0.98
    лия
    -0.96
    yorsunuz
    -0.96
    lloworld
    -0.94
    帖最后由
    -0.94
     ayaa
    -0.94
    authier
    -0.94
    urii
    -0.93
    ｖ
    -0.93
    POSITIVE LOGITS
     like
    1.05
     money
    1.02
     payment
    0.99
     these
    0.96
    ID
    0.96
     mueble
    0.95
     would
    0.95
     fees
    0.94
     that
    0.94
     comments
    0.93
    Activations Density 0.005%

    No Known Activations