© 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. 22-GEMMASCOPE-RES-131K
    7. 64612
    Prev
    Next
    INDEX
    Explanations

    describing initiation or conclusion

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sometimes
    -0.98
     inscri
    -0.95
     TOOL
    -0.94
    说说
    -0.91
    felves
    -0.88
    を含
    -0.88
     professionelle
    -0.88
     complexe
    -0.87
     nowych
    -0.87
    當天
    -0.87
    POSITIVE LOGITS
    匝
    0.93
     casi
    0.92
     haha
    0.91
     integrand
    0.91
    uzzi
    0.88
     comprehensive
    0.87
     głównie
    0.86
    oader
    0.86
    姻
    0.85
    ()):
    0.84
    Activations Density 0.072%

    No Known Activations