© 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. 12162
    Prev
    Next
    INDEX
    Explanations

    /bin/ paths

    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
     $("
    0.91
     Corruption
    0.87
    лося
    0.85
     Refunds
    0.85
    esque
    0.84
     Coupons
    0.84
     Corner
    0.82
     によって
    0.81
     改
    0.81
     Wiring
    0.81
    POSITIVE LOGITS
    bin
    1.05
    ulose
    1.01
    طان
    1.01
     viện
    0.98
    sbin
    0.97
    ttemberg
    0.95
    ORIAL
    0.93
    robot
    0.91
    нняя
    0.91
    𝗼
    0.90
    Activations Density 0.004%

    No Known Activations