© 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. 174782
    Prev
    Next
    INDEX
    Explanations

    foreign names and percentages

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

    legal ramifications

    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
     print
    0.48
     export
    0.46
    \"
    0.46
     exporting
    0.45
    vai
    0.44
    秆
    0.44
    USE
    0.43
     Export
    0.42
     változat
    0.42
    CAR
    0.42
    POSITIVE LOGITS
     Guillaume
    0.54
     まま
    0.50
     coscienza
    0.49
     ciertas
    0.46
     কাজী
    0.46
    䙲
    0.44
    ínas
    0.44
     Cristina
    0.43
     Dirac
    0.42
    砶
    0.42
    Activations Density 0.000%

    No Known Activations