© 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. 71885
    Prev
    Next
    INDEX
    Explanations

    personal history details

    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
     as
    -1.06
    an
    -1.03
     at
    -1.02
     in
    -1.02
     will
    -0.95
     cuando
    -0.93
    de
    -0.92
     while
    -0.92
    dez
    -0.92
    hibernate
    -0.92
    POSITIVE LOGITS
     recent
    1.60
     récente
    1.49
     previous
    1.42
     recently
    1.42
     current
    1.39
     history
    1.38
    recently
    1.37
    Recently
    1.33
     maravill
    1.29
     recente
    1.29
    Activations Density 0.054%

    No Known Activations