© 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. 16554
    Prev
    Next
    INDEX
    Explanations

    know how to

    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
    cterms
    -1.31
    宬
    -1.11
    tvguide
    -1.10
    panasonic
    -1.07
    artney
    -1.05
    浤
    -1.04
    の人生
    -1.03
    言った
    -1.01
    orescence
    -1.01
    xmax
    -1.00
    POSITIVE LOGITS
     that
    1.56
     how
    1.16
     conde
    1.15
     lamenta
    1.14
     intrig
    1.13
     extraordin
    1.12
     pernic
    1.10
     promete
    1.09
     herren
    1.08
     emble
    1.08
    Activations Density 0.003%

    No Known Activations