© 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-16K
    7. 2140
    Prev
    Next
    INDEX
    Explanations

    key for list items

    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_16k_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
    𝙣
    1.70
    𝙖
    1.59
    ئة
    1.57
    𝙧
    1.54
    𝐢
    1.54
    ה
    1.54
    ن
    1.51
    考える
    1.50
    𝐫
    1.50
    개의
    1.49
    POSITIVE LOGITS
    ractions
    1.43
    raction
    1.37
    luk
    1.36
    subdir
    1.35
    তম
    1.32
    Renewal
    1.31
    timber
    1.30
    Reducing
    1.29
    rejected
    1.27
    sust
    1.25
    Activations Density 0.011%

    No Known Activations