© 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. 177836
    Prev
    Next
    INDEX
    Explanations

    factors, we, just, local, usual

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

    resource allocation decisions

    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
     dinners
    0.41
    :-
    0.40
     एकत्र
    0.40
     Bracelet
    0.39
    า
    0.39
    bracelet
    0.39
     σύ
    0.38
    formed
    0.38
     Bingham
    0.38
     bracelet
    0.38
    POSITIVE LOGITS
     özellik
    0.50
     morf
    0.48
    ٹن
    0.48
    듄
    0.47
     tabii
    0.47
     características
    0.46
     constricted
    0.46
     khas
    0.45
     कैटेगरी
    0.45
     institucional
    0.45
    Activations Density 0.001%

    No Known Activations