© 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. 239962
    Prev
    Next
    INDEX
    Explanations

    centrally via

    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
    CONS
    0.47
    glass
    0.46
    amore
    0.44
    osph
    0.44
    mill
    0.44
    पर
    0.43
    もっと
    0.43
    5
    0.43
    २
    0.43
    esh
    0.43
    POSITIVE LOGITS
     biologie
    0.52
     Nauchno
    0.50
     centrifugation
    0.50
     Freude
    0.49
     confidentialité
    0.48
     Kidman
    0.48
     Süden
    0.46
     réaction
    0.46
     চার
    0.46
     €.
    0.46
    Activations Density 0.001%

    No Known Activations