© 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. 110928
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    quick check

    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
    a
    0.62
    um
    0.55
     as
    0.53
     प्रद
    0.52
     και
    0.48
    re
    0.48
    pr
    0.46
    eh
    0.46
    transit
    0.46
     Gay
    0.46
    POSITIVE LOGITS
    <>();
    0.49
    وریت
    0.49
    愔
    0.48
    见面
    0.48
    يري
    0.47
    톄
    0.47
     بالټ
    0.46
     సమావేశ
    0.46
    nPortIndex
    0.46
    訢
    0.46
    Activations Density 0.001%

    No Known Activations