© 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. 116271
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
     by
    -1.34
     then
    -1.20
     of
    -1.19
     each
    -1.08
     every
    -1.02
    il
    -0.98
     even
    -0.96
     not
    -0.96
     or
    -0.95
     both
    -0.95
    POSITIVE LOGITS
     while
    1.91
     mentre
    1.48
     mientras
    1.34
     whilst
    1.32
     enquanto
    1.20
    while
    1.16
    ながら
    1.13
    ırken
    1.13
     accompany
    1.08
     المعيار
    1.06
    Activations Density 0.025%

    No Known Activations