© 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. 26837
    Prev
    Next
    INDEX
    Explanations

    possibility or permission

    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
    in
    0.77
    न
    0.69
    ن
    0.61
    ম
    0.61
    inį
    0.59
    ン
    0.59
    보
    0.59
    م
    0.58
    ியை
    0.57
    𝟰
    0.57
    POSITIVE LOGITS
     may
    0.66
     was
    0.65
    clerc
    0.56
     и
    0.55
     και
    0.55
     vary
    0.54
     પરંતુ
    0.53
    .}
    0.53
    ։
    0.52
     نیز
    0.52
    Activations Density 0.026%

    No Known Activations