© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191602
    Prev
    Next
    INDEX
    Explanations

    Limit, harm, physical, mentioned, DataFrame

    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_40_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
     HEAD
    0.38
     double
    0.37
    ਉ
    0.37
    一行
    0.37
    Elle
    0.36
    роў
    0.36
    orean
    0.36
    сього
    0.36
    Ell
    0.35
    torio
    0.35
    POSITIVE LOGITS
     régional
    0.43
     país
    0.42
    ctuations
    0.41
    চনা
    0.39
    ریف
    0.39
     nación
    0.39
     سیاسی
    0.38
    striction
    0.38
     ܠ
    0.38
     ratione
    0.38
    Activations Density 0.000%

    No Known Activations