© 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. 111679
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     znamená
    0.54
    둴
    0.52
    Khokhlov
    0.52
     ሁኔታ
    0.51
    Ǘ
    0.51
     millió
    0.50
    вина
    0.50
    倬
    0.49
    ዔ
    0.49
    琹
    0.49
    POSITIVE LOGITS
     and
    0.76
     to
    0.67
    to
    0.67
     or
    0.65
     at
    0.64
    ,
    0.63
     of
    0.62
    -
    0.61
    /
    0.61
     d
    0.59
    Activations Density 0.002%

    No Known Activations