© 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. 22-GEMMASCOPE-2-RES-262K
    7. 12271
    Prev
    Next
    INDEX
    Explanations

    emoticons and ASCII art faces

    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_22_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
    Types
    0.95
    Classic
    0.94
    uomo
    0.94
    e
    0.92
    sar
    0.90
    saf
    0.89
    Vintage
    0.89
    Virt
    0.88
    😊
    0.88
    RPM
    0.87
    POSITIVE LOGITS
     <
    0.92
     thin
    0.89
     >
    0.85
     metavar
    0.81
     sau
    0.79
     ou
    0.77
     [<
    0.77
    ಲ್‌
    0.76
     esa
    0.76
     ese
    0.75
    Activations Density 0.003%

    No Known Activations