© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10951
    Prev
    Next
    INDEX
    Explanations

    where LLM research is headed

    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
    9
    0.78
    tahun
    0.74
    ла
    0.71
     individualism
    0.71
    8
    0.70
    ត្
    0.69
     করিতেন
    0.67
     silam
    0.67
    했던
    0.67
     щодо
    0.65
    POSITIVE LOGITS
     uygun
    0.75
     bisa
    0.74
     puede
    0.71
     budding
    0.70
     একটি
    0.69
     costume
    0.68
    樣子
    0.67
     dashing
    0.66
     ২
    0.66
     clever
    0.66
    Activations Density 0.166%

    No Known Activations