© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10564
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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_9_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
    ️
    0.66
    
    0.61
    {}",
    0.58
    en
    0.57
    ת
    0.56
    k
    0.56
    ed
    0.55
    as
    0.54
    {}".
    0.51
    ་
    0.51
    POSITIVE LOGITS
    veloppement
    0.60
    КУ
    0.55
    Trước
    0.52
    ـ
    0.52
    женные
    0.51
     brill
    0.51
    व
    0.50
     выпу
    0.50
     والم
    0.49
     Основ
    0.49
    Activations Density 0.304%

    No Known Activations