© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138774
    Prev
    Next
    INDEX
    Explanations

    lists of items and detailed explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    篌
    0.46
    izada
    0.45
    Я
    0.44
    ened
    0.43
     turt
    0.43
    Architect
    0.43
     alba
    0.43
    G
    0.43
    ian
    0.42
    Y
    0.42
    POSITIVE LOGITS
     diffère
    0.45
     compliqué
    0.44
    নার
    0.43
     CallOptions
    0.43
     Malgré
    0.43
     malgré
    0.42
     accuses
    0.41
    မှုကို
    0.41
     নির্ভ
    0.41
     superiori
    0.41
    Activations Density 0.001%

    No Known Activations