© 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. 94936
    Prev
    Next
    INDEX
    Explanations

    defining or stating facts

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

    tracking collections behaviors

    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
    难题
    0.47
     pove
    0.45
     nouveaux
    0.44
     nuevos
    0.42
     calitate
    0.42
    进口
    0.41
    とは
    0.41
    ﻞ
    0.41
     nuevas
    0.41
     questione
    0.41
    POSITIVE LOGITS
    profitable
    0.47
     volunteered
    0.46
    ⮚
    0.45
    aze
    0.45
     Вайлд
    0.44
    অতি
    0.43
     thaliana
    0.43
    ؛
    0.43
    certs
    0.43
    );
    0.43
    Activations Density 0.002%

    No Known Activations