© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208214
    Prev
    Next
    INDEX
    Explanations

    products

    np_acts-logits-general · gemini-2.5-flash-lite

    continue to response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ון
    0.52
     projector
    0.45
    ⓪
    0.44
    ਨੀ
    0.43
     பகை
    0.43
     幅
    0.43
     ঐতিহ্য
    0.42
     неё
    0.42
    QtGui
    0.42
    (__('
    0.42
    POSITIVE LOGITS
    inta
    0.52
    rog
    0.50
    ross
    0.49
    gam
    0.49
    bid
    0.46
    encie
    0.45
    rence
    0.45
    atang
    0.45
    rost
    0.44
     Dopp
    0.44
    Activations Density 0.000%

    No Known Activations