© 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. 39972
    Prev
    Next
    INDEX
    Explanations

    server farm

    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
    ب
    0.53
    ousing
    0.46
    isors
    0.43
    as
    0.42
    bolos
    0.42
    ान
    0.41
    owing
    0.41
    ন
    0.41
    ᴙ
    0.40
    ம்
    0.40
    POSITIVE LOGITS
     Macy
    0.46
     sytu
    0.45
     oggetto
    0.45
    縣
    0.43
    เมือง
    0.42
     webhook
    0.42
     ก่อน
    0.40
     cityName
    0.40
     Watson
    0.40
    同じ
    0.39
    Activations Density 0.001%

    No Known Activations