© 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. 34-GEMMASCOPE-RES-131K
    7. 30034
    Prev
    Next
    INDEX
    Explanations

    wrestling names

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     considerably
    -0.79
     fans
    -0.76
     honestly
    -0.75
     severely
    -0.75
    平日
    -0.73
     Arrested
    -0.73
     specialization
    -0.73
     everybody
    -0.73
     nobody
    -0.72
    要望
    -0.71
    POSITIVE LOGITS
     CAME
    0.92
     Zayn
    0.91
    кара
    0.85
     Dij
    0.85
     دار
    0.82
     Pogba
    0.82
    Į
    0.82
    rée
    0.82
    initions
    0.81
     Lexus
    0.80
    Activations Density 0.012%

    No Known Activations