© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146360
    Prev
    Next
    INDEX
    Explanations

    Entry followed by colon

    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_29_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
     Suppliers
    1.03
    zj
    0.97
     dwind
    0.95
     corset
    0.90
    ⒈
    0.90
    騨
    0.89
     paypal
    0.89
     unpredict
    0.88
    린
    0.88
    پے
    0.87
    POSITIVE LOGITS
    EM
    1.10
    à
    0.96
    emo
    0.94
    ancienne
    0.88
     sì
    0.85
    Era
    0.84
     individual
    0.84
    américa
    0.84
    Ä
    0.84
     ges
    0.84
    Activations Density 0.000%

    No Known Activations