© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70453
    Prev
    Next
    INDEX
    Explanations

    ID or identifier strings

    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
     restante
    -1.00
     some
    -0.97
     and
    -0.94
    prone
    -0.93
    塑造
    -0.93
    #![
    -0.92
    mainly
    -0.91
    velser
    -0.91
     viver
    -0.90
     about
    -0.90
    POSITIVE LOGITS
     betaling
    1.14
     mengerti
    1.10
     бампер
    1.09
     or
    1.02
    moires
    1.01
     gevol
    1.01
    elesaikan
    1.01
     involucrados
    1.00
     gezondheid
    0.99
     mengapa
    0.98
    Activations Density 0.011%

    No Known Activations