© 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. 112736
    Prev
    Next
    INDEX
    Explanations

    common functions

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

    UART communication or Special Relativity

    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
    Nullable
    0.47
    ONSE
    0.46
    ালোচনা
    0.45
     Jahrze
    0.45
    ೆಂ
    0.45
     thập
    0.44
    ﻨ
    0.43
    Neal
    0.42
    ｫ
    0.42
    䚲
    0.42
    POSITIVE LOGITS
     sequ
    0.43
     wonder
    0.42
    局部
    0.42
    衣装
    0.42
     руководитель
    0.41
     imitation
    0.41
     تعلق
    0.41
    头
    0.41
     mering
    0.40
     Geburtstag
    0.40
    Activations Density 0.002%

    No Known Activations