© 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. 22-GEMMASCOPE-RES-131K
    7. 33249
    Prev
    Next
    INDEX
    Explanations

    code termination or variable naming

    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
     notas
    -1.02
     bolsa
    -0.94
     egiten
    -0.91
     للغاية
    -0.91
     latas
    -0.89
     gotas
    -0.89
     kritis
    -0.85
    tyimages
    -0.84
     punya
    -0.84
     Rolex
    -0.84
    POSITIVE LOGITS
     then
    1.04
    /*
    1.02
    中午
    1.00
     algumas
    0.98
    有些人
    0.95
     alguns
    0.93
    那天
    0.93
    ("'"
    0.92
     ankaŭ
    0.90
    [\
    0.88
    Activations Density 0.001%

    No Known Activations