© 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. 32667
    Prev
    Next
    INDEX
    Explanations

    but it does

    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
    Negative Logits
     étages
    -1.23
     ولكن
    -1.16
     naturellement
    -1.15
    yadi
    -1.11
     schuldig
    -1.10
     but
    -1.08
    aunque
    -1.05
     zwar
    -1.05
    ditionally
    -1.04
     αλλά
    -1.03
    POSITIVE LOGITS
     still
    1.38
     nonetheless
    1.34
     useful
    1.32
     nevertheless
    1.31
     also
    1.31
     could
    1.26
     immerhin
    1.20
     what
    1.15
     helpful
    1.13
     will
    1.12
    Activations Density 0.025%

    No Known Activations