© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    title slides and keywords

    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
     ಪು
    0.54
    防控
    0.48
    榞
    0.48
    स्तु
    0.47
    程度の
    0.47
     ક્
    0.47
    景观
    0.46
    នៅក្នុង
    0.46
    感恩
    0.45
    티
    0.45
    POSITIVE LOGITS
    ir
    0.66
    azawa
    0.52
    io
    0.50
    ע
    0.49
    ob
    0.47
    ck
    0.46
    ai
    0.46
    Accounting
    0.45
    No
    0.45
    it
    0.45
    Activations Density 0.001%

    No Known Activations