© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81637
    Prev
    Next
    INDEX
    Explanations

    new developments and current times

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

    earliest convenience / as soon as possible

    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
    Negative Logits
    박
    0.46
     tronc
    0.45
     allocate
    0.42
     utiles
    0.42
    ванный
    0.41
    الب
    0.41
     liters
    0.41
    시아
    0.41
     쿠
    0.41
     wyra
    0.40
    POSITIVE LOGITS
    ern
    0.48
    itude
    0.47
    emetery
    0.46
    incinnati
    0.46
    ett
    0.46
    elle
    0.45
    ?
    0.44
    ochemistry
    0.44
    är
    0.43
     Stations
    0.42
    Activations Density 0.000%

    No Known Activations