© 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. 106894
    Prev
    Next
    INDEX
    Explanations

    rental services

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

    specialized technical jargon

    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
    нг
    0.57
    кона
    0.53
    п
    0.52
     बेहत
    0.50
    ницу
    0.49
    лдуу
    0.49
     улучшения
    0.47
    helping
    0.47
    л
    0.46
     Хоккей
    0.46
    POSITIVE LOGITS
     forhold
    0.46
     yrs
    0.46
     mw
    0.45
     datasheet
    0.44
     YEARS
    0.44
    ConstPtr
    0.44
     pwd
    0.43
    两年
    0.43
     allerede
    0.43
     vapeur
    0.43
    Activations Density 0.005%

    No Known Activations