© 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. 25419
    Prev
    Next
    INDEX
    Explanations

    adjusting values in settings

    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
    க்கர
    0.52
    艿
    0.50
     that
    0.47
    \}$,
    0.44
    $.
    0.44
    徐
    0.44
    सरण
    0.44
    적인
    0.44
    >),
    0.43
     größeren
    0.43
    POSITIVE LOGITS
    fonte
    0.47
     proclaims
    0.44
    ่
    0.44
    o
    0.43
    на
    0.43
     suave
    0.42
    ↵
    0.42
     I
    0.42
     donn
    0.41
     (
    0.41
    Activations Density 0.010%

    No Known Activations