© 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. 10-GEMMASCOPE-RES-131K
    7. 20657
    Prev
    Next
    INDEX
    Explanations

    tennis, sports

    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_10/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
     SOME
    -1.70
     EVER
    -1.60
    However
    -1.55
     ANY
    -1.53
    j
    -1.49
    냑
    -1.48
     WHEN
    -1.46
    9
    -1.41
     هي
    -1.39
     jednak
    -1.39
    POSITIVE LOGITS
     like
    1.51
    gendes
    1.34
     postes
    1.30
     такого
    1.28
     certificat
    1.27
    聿
    1.27
     tantas
    1.27
     Feu
    1.27
    cension
    1.25
    Endor
    1.25
    Activations Density 0.002%

    No Known Activations