© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32897
    Prev
    Next
    INDEX
    Explanations

    HTML class, id, role attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -1.37
     only
    -1.25
     through
    -1.16
     until
    -1.14
     as
    -1.13
     which
    -1.13
     and
    -1.12
     gets
    -1.09
     any
    -1.09
     carefully
    -1.08
    POSITIVE LOGITS
     enfermos
    1.20
     nè
    1.16
     faisaient
    1.13
     zó
    1.13
     comigo
    1.10
     “
    1.10
     eten
    1.07
    каун
    1.07
     '"
    1.06
    lunda
    1.06
    Activations Density 0.003%

    No Known Activations