© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71349
    Prev
    Next
    INDEX
    Explanations

    √ runs

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

    mountains of

    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
    Negative Logits
    печа
    0.42
     преда
    0.42
    라우
    0.39
    കാ
    0.39
    <unused2153>
    0.39
    ચી
    0.39
    다라고
    0.38
    dard
    0.38
    aderamente
    0.38
    ючись
    0.38
    POSITIVE LOGITS
     entière
    0.43
     زمین
    0.41
    ()!=
    0.41
    番
    0.41
     OE
    0.40
     multiplicity
    0.38
     company
    0.38
    isel
    0.38
     Ừ
    0.38
     onus
    0.38
    Activations Density 0.001%

    No Known Activations