© 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. 229634
    Prev
    Next
    INDEX
    Explanations

    maritime, application, driving, addicted

    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
    Ни
    0.48
     controlar
    0.48
     Controlador
    0.48
     licenciatura
    0.48
    샅
    0.47
    이미
    0.47
    관리
    0.46
     batalla
    0.46
    പ
    0.46
     Talia
    0.45
    POSITIVE LOGITS
     \
    0.53
    ského
    0.44
    ...)
    0.44
    plo
    0.43
     coveted
    0.43
    ynd
    0.42
     \}
    0.41
    ច្រើន
    0.41
     backward
    0.39
     ine
    0.39
    Activations Density 0.000%

    No Known Activations