© 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. 40-GEMMASCOPE-2-RES-262K
    4. 777
    Prev
    Next
    INDEX
    Explanations

    Hacks primarily verse engineer

    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
    ологии
    0.43
    қ
    0.43
    re
    0.42
     भाजपा
    0.42
    ו
    0.41
    /////////
    0.41
    disable
    0.40
    日付
    0.40
    ಲಾಯಿತು
    0.40
    뭉
    0.40
    POSITIVE LOGITS
     متش
    0.51
     Tons
    0.51
     probiotics
    0.48
     تنس
    0.46
    :
    0.46
     vô
    0.46
     đổ
    0.46
     القلب
    0.45
    ški
    0.45
     armature
    0.45
    Activations Density 0.000%

    No Known Activations