© 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. 86610
    Prev
    Next
    INDEX
    Explanations

    due to or call for

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

    deduce, plan, regulator, played, UI

    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
    ﺪ
    0.52
    ﾋ
    0.49
    дание
    0.48
    ঃ
    0.47
    ﻭ
    0.47
    OUS
    0.47
    ಮ್ಮೆ
    0.47
    هرة
    0.46
    ﺓ
    0.46
    ﻀ
    0.46
    POSITIVE LOGITS
     karakteristik
    0.52
     giriş
    0.48
     Diagnostics
    0.47
     Nov
    0.47
     Essentials
    0.46
     kulland
    0.45
     kre
    0.44
     Place
    0.44
     quercetin
    0.44
     Diagnostic
    0.44
    Activations Density 0.001%

    No Known Activations