© 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. 32842
    Prev
    Next
    INDEX
    Explanations

    couple 'Baccapuru'

    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
     For
    -1.18
    ogues
    -1.16
    各式
    -1.05
    onomies
    -1.04
    chiato
    -1.04
    ira
    -1.02
     varias
    -1.01
    :{
    -1.01
    ..."
    -1.01
     $-$
    -1.01
    POSITIVE LOGITS
     zwi
    1.39
     vingt
    1.37
     largeur
    1.34
     gants
    1.30
     bouteille
    1.20
     rése
    1.20
     rouleau
    1.20
     luks
    1.19
     paille
    1.19
     úteis
    1.14
    Activations Density 0.133%

    No Known Activations