© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30929
    Prev
    Next
    INDEX
    Explanations

    IN THE UNITED STATES COURT OF APPEALS

    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
    Not in Any Lists

    No Comments

    Negative Logits
     because
    -1.06
     from
    -1.04
     very
    -0.95
     although
    -0.95
     while
    -0.94
     despite
    -0.93
     after
    -0.90
     during
    -0.87
     meticulous
    -0.87
     tré
    -0.86
    POSITIVE LOGITS
    ↵↵↵
    0.91
     definiert
    0.90
    其他人
    0.87
    sumowanie
    0.85
    Vw
    0.84
    identified
    0.83
     atteindre
    0.82
    فایل‌لار
    0.82
    potentially
    0.81
     iniz
    0.81
    Activations Density 0.002%

    No Known Activations