© 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. 35312
    Prev
    Next
    INDEX
    Explanations

    telling a story

    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
    ↵↵
    -0.95
     Си
    -0.93
    ↵↵↵
    -0.93
     VAR
    -0.87
    "].
    -0.84
     can
    -0.84
     к
    -0.84
     also
    -0.84
     Articles
    -0.84
     avenue
    -0.82
    POSITIVE LOGITS
     about
    1.57
     stories
    1.40
     story
    1.36
     that
    1.27
     STORIES
    1.20
     how
    1.14
     STORY
    1.14
    tale
    1.12
    orexia
    1.09
     tale
    1.06
    Activations Density 0.044%

    No Known Activations