© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4717
    Prev
    Next
    INDEX
    Explanations

    as of [date]

    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
    0
    0.52
     crecimiento
    0.38
     deploy
    0.37
     crescita
    0.36
    iew
    0.35
    ichiro
    0.35
    is
    0.34
    ence
    0.34
     verano
    0.34
    ak
    0.33
    POSITIVE LOGITS
     பாம்ப
    0.44
     ಮತ್ತು
    0.43
    ریف
    0.43
    われている
    0.43
    𝗡
    0.42
    𝚛
    0.42
    🄴
    0.42
    <unused1757>
    0.42
     میرے
    0.42
    ম্মদ
    0.42
    Activations Density 0.020%

    No Known Activations