© 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. 139
    Prev
    Next
    INDEX
    Explanations

    you and suggesting similar actions

    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
    смарт
    -0.97
     Lycée
    -0.91
     Modes
    -0.89
     armées
    -0.88
    undo
    -0.86
     koala
    -0.86
     INGRED
    -0.85
     peered
    -0.84
     there
    -0.84
     at
    -0.83
    POSITIVE LOGITS
     similar
    1.73
     podob
    1.63
    Similar
    1.57
     similarly
    1.56
    similar
    1.53
     подоб
    1.46
    Similarly
    1.46
     тоже
    1.45
     ebenfalls
    1.44
     Similar
    1.35
    Activations Density 0.039%

    No Known Activations