© 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. 147629
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    hollow, balancing, exact, way

    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
    from
    0.52
    ૧
    0.51
    ১
    0.50
     назна
    0.46
     промышленности
    0.46
    一起来
    0.46
    ㄱ
    0.45
    to
    0.44
    gain
    0.44
    rs
    0.44
    POSITIVE LOGITS
     involution
    0.49
     sensi
    0.48
    श्किल
    0.46
     prácticas
    0.46
     habitudes
    0.45
    وح
    0.44
     identifik
    0.44
    嗇
    0.44
     ktorá
    0.43
     elenc
    0.43
    Activations Density 0.000%

    No Known Activations