© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193798
    Prev
    Next
    INDEX
    Explanations

    titles of media and products

    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
     იაპ
    0.64
    瘓
    0.59
    Japanese
    0.58
    ญี่ป
    0.57
    japanese
    0.56
     Япо
    0.56
     Japanese
    0.53
     konusu
    0.52
     япон
    0.51
    Totals
    0.51
    POSITIVE LOGITS
    ・
    0.60
     【
    0.58
    ≒
    0.58
    （
    0.57
    ＜
    0.57
    ×
    0.56
    ★
    0.56
    ＝
    0.56
    〜
    0.54
    ∞
    0.53
    Activations Density 0.006%

    No Known Activations