© 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. 229504
    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
    ál
    0.50
    vall
    0.47
    <0xD5>
    0.46
    lendi
    0.46
    journ
    0.44
    íj
    0.44
    âm
    0.43
    paramet
    0.43
    fü
    0.43
    ney
    0.43
    POSITIVE LOGITS
     CERT
    0.46
     AMERICA
    0.44
    砾
    0.43
     Nebraska
    0.43
     fax
    0.41
     SOAP
    0.41
     eurozone
    0.40
     certification
    0.40
     workbook
    0.40
     Warranty
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.