© 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. 102374
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    connect depend find equivalents

    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
    does
    0.54
    tidak
    0.50
     光
    0.48
     一般
    0.47
     चैंपियनशिप
    0.47
     問
    0.45
     يست
    0.45
     LIMITED
    0.45
     絶対
    0.45
     群
    0.45
    POSITIVE LOGITS
     Mediterr
    0.44
    Tween
    0.44
    вої
    0.44
     réalisée
    0.43
     técnica
    0.42
    ée
    0.41
     vannak
    0.41
    绀
    0.41
     réalisé
    0.40
     lèvres
    0.40
    Activations Density 0.001%

    No Known Activations