© 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. 5856
    Prev
    Next
    INDEX
    Explanations

    book titles and descriptions

    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
    ka
    0.42
    ia
    0.39
    za
    0.39
    ه‌
    0.39
    ร
    0.38
    Ī
    0.38
    ar
    0.37
    -
    0.36
     fáb
    0.36
    ラ
    0.36
    POSITIVE LOGITS
     The
    0.56
     व्हाट
    0.56
     WITH
    0.53
    <unused619>
    0.53
     A
    0.52
     어떻게
    0.49
    <unused235>
    0.49
     How
    0.49
    <unused650>
    0.49
    <unused1868>
    0.48
    Activations Density 0.000%

    No Known Activations