© 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. 41751
    Prev
    Next
    INDEX
    Explanations

    numerical ranges

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

    ranges of numbers and currency

    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
     nejen
    0.46
    无论是
    0.42
    =[];
    0.41
    tena
    0.40
     tại
    0.39
     $,
    0.39
     .,
    0.39
     …,
    0.38
    ativ
    0.38
     реги
    0.38
    POSITIVE LOGITS
    Depends
    0.49
    Depending
    0.49
    PACKAGE
    0.48
    Ｑ
    0.48
     quantité
    0.46
    Quantidade
    0.45
    depending
    0.44
    BUR
    0.43
    Exceptionally
    0.43
    개
    0.43
    Activations Density 0.037%

    No Known Activations