© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149098
    Prev
    Next
    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    เด
    0.76
     }}=\
    0.75
    ギア
    0.74
    ៦
    0.71
     сцена
    0.71
     strangle
    0.70
     ബാല
    0.70
    逗
    0.68
     เด
    0.68
     Strokes
    0.68
    POSITIVE LOGITS
    埙
    0.63
     contracting
    0.62
    क्षम
    0.62
    可以用
    0.60
    솥
    0.60
    <unused284>
    0.60
    ermak
    0.56
    াহিনী
    0.55
     लवकर
    0.55
    ственного
    0.55
    Activations Density 0.001%

    No Known Activations