© 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. 26641
    Prev
    Next
    INDEX
    Explanations

    sports and competition

    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
     nubes
    -1.35
    それほど
    -1.32
     היתה
    -1.26
    😹
    -1.23
     पनि
    -1.22
     ccm
    -1.20
    😻
    -1.19
     läßt
    -1.17
     BufferedWriter
    -1.17
    Bereich
    -1.16
    POSITIVE LOGITS
     токси
    1.25
    ņi
    1.23
     mencionó
    1.21
    『
    1.20
    toxicity
    1.20
    casted
    1.20
     probablemente
    1.17
    我看
    1.17
    ItemGroup
    1.15
     Из
    1.13
    Activations Density 0.017%

    No Known Activations