© 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. 17236
    Prev
    Next
    INDEX
    Explanations

    don't hesitate to give opinions

    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
     lucht
    0.41
    ၢ
    0.41
     eddies
    0.39
     Governments
    0.39
     processos
    0.38
     droughts
    0.38
     rupani
    0.38
     bearbeitet
    0.38
    artoum
    0.38
     aquifers
    0.38
    POSITIVE LOGITS
    ที่คุณ
    0.50
     headlines
    0.44
    wner
    0.43
     discolor
    0.42
    ount
    0.41
    ෆ
    0.41
     үнд
    0.40
    𝗧
    0.40
    rior
    0.40
     당신
    0.40
    Activations Density 0.001%

    No Known Activations