© 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-65K
    7. 11032
    Prev
    Next
    INDEX
    Explanations

    lists ending with and more!

    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_65k_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
     مثلا
    0.63
     or
    0.54
     etc
    0.54
    0.50
     I
    0.49
    and
    0.49
     و
    0.49
     или
    0.47
     например
    0.47
    /[
    0.47
    POSITIVE LOGITS
    ття
    0.56
     niż
    0.55
    ப்பட்டது
    0.54
     vibrant
    0.54
    !।
    0.53
     buzzing
    0.53
     countless
    0.52
    на
    0.52
    лся
    0.52
    ப்பட்டுள்ளது
    0.51
    Activations Density 0.027%

    No Known Activations