© 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. 121322
    Prev
    Next
    INDEX
    Explanations

    ordered banks

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

    linking abstract concepts to examples

    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
    天
    0.49
    خل
    0.43
    吔
    0.43
    感受到
    0.42
    ски
    0.42
    共有
    0.42
    共
    0.42
    ле
    0.41
    يل
    0.41
    住宅
    0.41
    POSITIVE LOGITS
    foss
    0.52
    isto
    0.50
    iania
    0.49
     imperialism
    0.49
    􀂾
    0.49
     vaporization
    0.48
     infancy
    0.46
     ð
    0.46
    ’;
    0.46
    fus
    0.46
    Activations Density 0.002%

    No Known Activations