© 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. 108332
    Prev
    Next
    INDEX
    Explanations

    matching strings and algorithms

    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
    约定
    -0.73
     forester
    -0.73
     EY
    -0.73
     Kie
    -0.72
    gde
    -0.72
    siblings
    -0.71
     crochet
    -0.70
    ROC
    -0.69
    યા
    -0.69
    bangan
    -0.69
    POSITIVE LOGITS
     matching
    1.57
     match
    1.54
     matched
    1.48
     matches
    1.46
     Match
    1.41
     unmatched
    1.38
     Matching
    1.34
    マッチ
    1.34
    matching
    1.33
    Matching
    1.30
    Activations Density 0.013%

    No Known Activations