© 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. 56733
    Prev
    Next
    INDEX
    Explanations

    programming syntax and foreign characters

    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
    租赁
    -0.91
    istió
    -0.88
    Ostat
    -0.82
    urcht
    -0.82
     istor
    -0.81
    お待ちしております
    -0.80
     gana
    -0.80
     crean
    -0.77
    ilustrasi
    -0.76
    になったら
    -0.76
    POSITIVE LOGITS
    ();
    1.10
    meldet
    0.94
     RSC
    0.90
     CTP
    0.88
    ));
    0.85
     سلام
    0.85
     biome
    0.85
     toán
    0.85
     MFA
    0.85
    ౪
    0.84
    Activations Density 0.000%

    No Known Activations