© 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. 37100
    Prev
    Next
    INDEX
    Explanations

    describing or analyzing trends

    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
    a
    0.61
    ه
    0.55
    S
    0.51
    i
    0.50
    ה
    0.49
    ланган
    0.46
    genommen
    0.46
    ي
    0.46
    manip
    0.46
    zné
    0.46
    POSITIVE LOGITS
     starfish
    0.46
    ুক্তি
    0.44
     kasih
    0.44
     Cheetah
    0.42
    粑
    0.42
     кораб
    0.41
    啥
    0.41
     babe
    0.40
     panther
    0.40
     Radiology
    0.40
    Activations Density 0.001%

    No Known Activations