© 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. 36638
    Prev
    Next
    INDEX
    Explanations

    code structure and filename context

    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
    痒
    0.47
    sete
    0.43
    ﾝ
    0.43
    ၊
    0.42
     imperialism
    0.42
    諄
    0.42
    :
    0.42
    嗲
    0.41
     ruth
    0.41
    และ
    0.41
    POSITIVE LOGITS
    is
    0.53
     />}
    0.43
    amanan
    0.42
    filename
    0.40
    Fil
    0.39
    িশ
    0.39
     Fil
    0.38
    uft
    0.38
    app
    0.38
    idelberg
    0.38
    Activations Density 0.005%

    No Known Activations