© 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. 11768
    Prev
    Next
    INDEX
    Explanations

    coin flips

    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
    al
    1.75
    at
    1.65
    uwa
    1.63
    et
    1.59
    d
    1.56
    s
    1.50
    ंडल
    1.49
    WindowState
    1.48
    水位
    1.47
    killers
    1.46
    POSITIVE LOGITS
    Х
    1.55
    А
    1.54
    Ƭ
    1.49
    这一点
    1.43
    Kabhi
    1.43
    üb
    1.36
    깃
    1.35
     покра
    1.34
     dio
    1.30
     micrographs
    1.30
    Activations Density 0.000%

    No Known Activations