© 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. 139687
    Prev
    Next
    INDEX
    Explanations

    dates and specific nouns

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

    positive difference

    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
    ﻌ
    0.54
    த்திரம்
    0.48
     അദ്ദേ
    0.48
    عدد
    0.47
    stringProp
    0.47
    carrito
    0.46
    cción
    0.46
    ^{'
    0.45
    ᱙
    0.45
    <unused984>
    0.45
    POSITIVE LOGITS
    (
    0.56
     mocy
    0.51
     eye
    0.50
     splicing
    0.49
    燊
    0.49
     (
    0.48
     Eye
    0.46
     splic
    0.46
     caer
    0.46
     encode
    0.44
    Activations Density 0.000%

    No Known Activations