© 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. 232763
    Prev
    Next
    INDEX
    Explanations

    option Benedict

    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
    난
    0.48
    هِ
    0.47
    هُ
    0.46
    出一个
    0.46
    ++);
    0.45
    ەند
    0.45
     replaceable
    0.45
     Redd
    0.44
    خوان
    0.43
    baan
    0.43
    POSITIVE LOGITS
    duration
    0.44
    discover
    0.44
     cier
    0.44
     그것
    0.43
     thisobject
    0.43
     তারপর
    0.42
     зимо
    0.42
     这
    0.41
    edos
    0.41
    তারপর
    0.41
    Activations Density 0.000%

    No Known Activations