© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    database identifiers

    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
    stacle
    -0.87
    bille
    -0.86
    lader
    -0.84
     KES
    -0.82
     Xy
    -0.82
     Gues
    -0.82
     MINOR
    -0.82
     BNB
    -0.80
     Boletín
    -0.79
     masculin
    -0.79
    POSITIVE LOGITS
     needed
    1.11
     options
    0.96
     requested
    0.93
     demand
    0.91
     what
    0.90
     desired
    0.90
     criteria
    0.87
     on
    0.87
     requirements
    0.86
     connaît
    0.86
    Activations Density 0.060%

    No Known Activations