© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77518
    Prev
    Next
    INDEX
    Explanations

    CGAL, CIGAR, CGImageRef, C.G. Jung, CG Cosmetic

    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
     altre
    -0.78
     эпо
    -0.74
    हो
    -0.72
    writel
    -0.72
    VIR
    -0.71
     رئیس
    -0.71
    痛い
    -0.71
    ACTOR
    -0.70
     Days
    -0.70
     MUL
    -0.69
    POSITIVE LOGITS
    cg
    1.09
     cg
    1.08
     CG
    1.00
    CG
    0.92
    Cg
    0.92
    ɦ
    0.83
    नलिखित
    0.80
    مؤ
    0.80
    不是很
    0.75
    おかげ
    0.74
    Activations Density 0.031%

    No Known Activations