© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    code structure parsing

    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
    cknowled
    1.03
    С
    1.00
    SF
    0.90
    ಕ
    0.89
    ございます
    0.88
    фта
    0.86
    О
    0.86
    ALSO
    0.86
    라
    0.86
    zak
    0.84
    POSITIVE LOGITS
    обходимо
    1.13
    spaper
    1.02
    ногда
    1.00
    pesar
    1.00
    ductory
    0.97
    spapers
    0.96
    প্রিল
    0.94
    orems
    0.93
    atomy
    0.92
    लंका
    0.92
    Activations Density 0.159%

    No Known Activations