© 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. 71056
    Prev
    Next
    INDEX
    Explanations

    in front of public view

    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
     imprescin
    -1.05
     ferru
    -0.97
    想了想
    -0.95
    étrie
    -0.94
     тонн
    -0.93
     ſu
    -0.92
     descricao
    -0.91
    editar
    -0.90
    plex
    -0.90
    reibt
    -0.90
    POSITIVE LOGITS
     public
    1.27
     embarrassing
    1.09
     embarrassed
    1.09
     other
    1.05
     embarrassment
    0.93
     several
    0.87
     embarrass
    0.87
     audience
    0.86
     堂
    0.84
    อื่น
    0.82
    Activations Density 0.018%

    No Known Activations