© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63094
    Prev
    Next
    INDEX
    Explanations

    legal document citations

    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_34/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
    ública
    -0.83
    뮤
    -0.81
    CHEMICAL
    -0.80
     Möglich
    -0.77
    ların
    -0.77
    ശ
    -0.74
    ké
    -0.74
     αυτή
    -0.72
    缤
    -0.72
     químicas
    -0.71
    POSITIVE LOGITS
    explained
    0.93
    unfortunately
    0.93
    trying
    0.91
     pescoço
    0.87
    considering
    0.87
    出色
    0.85
    可谓
    0.85
    believe
    0.85
     RULES
    0.84
     devast
    0.83
    Activations Density 0.102%

    No Known Activations