© 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. 252
    Prev
    Next
    INDEX
    Explanations

    point of

    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
    ámide
    -0.88
     the
    -0.87
     交換
    -0.85
    nă
    -0.84
     duży
    -0.83
    вели
    -0.83
    呐
    -0.79
    出来了
    -0.78
    catálogo
    -0.78
    过来了
    -0.77
    POSITIVE LOGITS
    <bos>
    1.33
    仕上がり
    0.90
    ...).
    0.88
    
    0.88
     
    0.86
    meteries
    0.85
    couraging
    0.84
    ährlich
    0.83
    nutie
    0.83
    geme
    0.82
    Activations Density 0.085%

    No Known Activations