© 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. 10933
    Prev
    Next
    INDEX
    Explanations

    client data structure

    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
    ir
    0.81
    ain
    0.77
    als
    0.71
    ag
    0.70
    <unused510>
    0.68
    ၊
    0.64
    atte
    0.62
    ोटा
    0.61
     វា
    0.60
    <unused615>
    0.60
    POSITIVE LOGITS
     decoupled
    0.95
    ING
    0.95
     seguir
    0.88
     inov
    0.88
     apertura
    0.86
     afet
    0.84
     disassemble
    0.84
     olho
    0.84
    VING
    0.83
     cursos
    0.82
    Activations Density 0.175%

    No Known Activations