© 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. 261029
    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
    Not in Any Lists

    No Comments

    Negative Logits
     جائیں
    0.47
    google
    0.47
    vers
    0.45
    goto
    0.45
     фабри
    0.45
    hebung
    0.44
     יה
    0.44
    W
    0.44
     суще
    0.43
     არს
    0.43
    POSITIVE LOGITS
     socials
    0.52
    မျှ
    0.51
     creatives
    0.50
     Hornets
    0.50
     attracts
    0.49
     sidelined
    0.49
     occupants
    0.49
     advertisers
    0.48
     insta
    0.48
     workplaces
    0.48
    Activations Density 0.000%

    No Known Activations