© 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. 20776
    Prev
    Next
    INDEX
    Explanations

    colors and hexadecimal codes

    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
     Fathers
    0.36
     Devlet
    0.35
     musia
    0.35
     ederim
    0.35
     savvy
    0.35
     industrious
    0.34
    าระ
    0.34
    飽
    0.33
    瑢
    0.33
     thunderstorm
    0.33
    POSITIVE LOGITS
    owa
    0.43
     यू
    0.40
     Еще
    0.40
     еще
    0.38
    的基础
    0.38
     founded
    0.37
     بدور
    0.37
    iftet
    0.37
    ネイル
    0.37
    ৳
    0.36
    Activations Density 0.005%

    No Known Activations