© 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. 164360
    Prev
    Next
    INDEX
    Explanations

    measuring or describing results

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

    executing concepts, roles, and items

    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
    ubi
    0.49
    ubic
    0.47
     ମ
    0.44
     Lauren
    0.44
    ows
    0.43
    ্যেষ্ঠ
    0.43
    uran
    0.42
    ā
    0.41
    മസ
    0.40
    ened
    0.40
    POSITIVE LOGITS
    ن
    0.55
    完全
    0.54
     executar
    0.54
     execução
    0.53
     exécut
    0.53
     analys
    0.52
    兄弟
    0.52
     возможно
    0.50
     ona
    0.50
    引
    0.50
    Activations Density 0.004%

    No Known Activations