© 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. 104453
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     first
    -0.93
     while
    -0.91
     Fußballspieler
    -0.89
     only
    -0.85
     slightly
    -0.85
    Приготовление
    -0.84
     if
    -0.84
    Отзывы
    -0.84
     $.
    -0.82
    imetric
    -0.82
    POSITIVE LOGITS
    soo
    0.94
    launched
    0.90
     hoặc
    0.88
    瞓
    0.88
     corriger
    0.85
     coté
    0.85
    knows
    0.84
    žo
    0.84
     ドレス
    0.83
    uis
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.