© 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. 261291
    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
     juc
    0.53
     indicador
    0.46
     filesize
    0.46
     年度
    0.45
     camere
    0.45
     ಸದಸ್ಯ
    0.44
     sampled
    0.44
     Насе
    0.44
    班
    0.44
    起来
    0.43
    POSITIVE LOGITS
     გ
    0.49
     rapproche
    0.48
     atrophy
    0.48
    èles
    0.47
    habitation
    0.46
     Това
    0.46
     stö
    0.44
     klart
    0.44
     Domains
    0.44
     เพราะ
    0.43
    Activations Density 0.000%

    No Known Activations