© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns or adjectives

    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
     علامت
    0.44
     رمز
    0.39
     हुआ
    0.38
    根據
    0.38
    採取
    0.38
    轂
    0.37
    гети
    0.37
    ђе
    0.36
     ראש
    0.36
    SLAM
    0.36
    POSITIVE LOGITS
    sg
    0.47
     !
    0.35
    s
    0.35
     navy
    0.34
    maha
    0.33
     will
    0.33
    eches
    0.33
     would
    0.33
    liver
    0.33
    rt
    0.33
    Activations Density 0.002%

    No Known Activations