© 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. 29
    Prev
    Next
    INDEX
    Explanations

    actions and processes

    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
    ی
    0.53
    র
    0.45
    ের
    0.44
    ال
    0.43
    它
    0.42
    사
    0.41
    ৭
    0.39
    ৯
    0.38
    나
    0.37
     looming
    0.36
    POSITIVE LOGITS
    -
    0.44
    ton
    0.38
     a
    0.35
    ting
    0.33
    <0xA3>
    0.32
    lessly
    0.32
     oneself
    0.32
    <0x80>
    0.31
    ,
    0.30
    tais
    0.30
    Activations Density 0.847%

    No Known Activations