© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    similarities across lists

    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
     pérd
    -0.99
    ([
    -0.98
    --
    -0.96
    —”
    -0.95
    Примі
    -0.95
    —“
    -0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.92
    Publié
    -0.92
    eará
    -0.91
     sopra
    -0.91
    POSITIVE LOGITS
     szint
    0.99
    Similarly
    0.96
     also
    0.95
     также
    0.94
     srebr
    0.93
     ebenfalls
    0.93
    ibid
    0.90
    CURRENT
    0.90
    ский
    0.90
    これも
    0.90
    Activations Density 0.251%

    No Known Activations