© 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. 261100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
     Musica
    0.51
     Beauty
    0.50
     beauty
    0.48
     Canaria
    0.48
     Retour
    0.47
     travaux
    0.47
     Withers
    0.46
     Selección
    0.46
    婼
    0.45
     belleza
    0.45
    POSITIVE LOGITS
    appan
    0.49
     改
    0.48
    hwa
    0.46
     որ
    0.45
    aklar
    0.45
     ত্রিশ
    0.45
    、【
    0.45
     金属
    0.44
     其中
    0.44
    }']
    0.44
    Activations Density 0.000%

    No Known Activations