© 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. 16891
    Prev
    Next
    INDEX
    Explanations

    self ,

    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
    স্তক
    0.43
     kobiety
    0.42
     بری
    0.41
     unités
    0.40
    Crew
    0.40
    物体
    0.40
     ฮ
    0.39
    ക്കാല
    0.39
     hátsó
    0.39
     কাতর
    0.39
    POSITIVE LOGITS
    ,
    0.47
    _,
    0.39
     individual
    0.37
    .
    0.36
    ev
    0.35
    \%,
    0.35
     manners
    0.34
     and
    0.34
    ЕН
    0.34
    શ
    0.34
    Activations Density 0.004%

    No Known Activations