© 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. 236550
    Prev
    Next
    INDEX
    Explanations

    time related words and non-English words

    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
     rinsed
    0.49
    ^{
    0.46
     habían
    0.46
     ahorro
    0.45
     शुरु
    0.45
    forcements
    0.45
    wnie
    0.45
     depreciation
    0.45
    ate
    0.44
     compensation
    0.44
    POSITIVE LOGITS
    см
    0.50
     القص
    0.48
    otricha
    0.45
     Palabra
    0.44
    ཋ
    0.43
     ലേഖ
    0.43
    專輯
    0.42
     carpeta
    0.42
     lumea
    0.42
     Obwohl
    0.42
    Activations Density 0.000%

    No Known Activations