© 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. 71215
    Prev
    Next
    INDEX
    Explanations

    analysis and pass

    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
    沢山
    -0.96
    gląda
    -0.94
    古い
    -0.88
     anticoag
    -0.85
    に行く
    -0.84
     pregunto
    -0.84
     zusätz
    -0.83
    ulpt
    -0.83
    ⌗
    -0.83
    sidenav
    -0.82
    POSITIVE LOGITS
     åren
    0.94
     mét
    0.90
     получил
    0.84
     Hø
    0.83
    κτηρισ
    0.82
    ஂ
    0.82
    ➢
    0.82
     CLA
    0.79
     disappoint
    0.79
     rotund
    0.79
    Activations Density 0.079%

    No Known Activations