© 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. 56570
    Prev
    Next
    INDEX
    Explanations

    organizational terms and approvals

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

    categorize and accept

    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
    +="
    0.45
    ientôt
    0.45
    half
    0.44
     racked
    0.43
    ಾಗಲೇ
    0.43
     ग्रस्त
    0.43
    comb
    0.42
     constricted
    0.41
    AIRE
    0.41
    -}$
    0.41
    POSITIVE LOGITS
     Audit
    0.53
     licencia
    0.51
     ...,
    0.51
     Access
    0.50
     essencial
    0.50
     Principles
    0.49
     Calendar
    0.48
     Languages
    0.48
     Hall
    0.48
     Halls
    0.48
    Activations Density 0.000%

    No Known Activations