© 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. 7026
    Prev
    Next
    INDEX
    Explanations

    Google, versions, base

    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
    夂
    0.33
    ütün
    0.33
    estab
    0.31
    Է
    0.30
    リエステル
    0.30
    Unser
    0.30
    amsa
    0.29
     zna
    0.28
    ześ
    0.28
    .??.??"]
    0.28
    POSITIVE LOGITS
    LY
    0.32
    কে
    0.32
     등
    0.29
     विरोध
    0.29
    UR
    0.28
    verages
    0.28
     Scaffold
    0.28
     차량
    0.28
    𝗺
    0.28
     کاهش
    0.28
    Activations Density 0.081%

    No Known Activations