© 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. 77309
    Prev
    Next
    INDEX
    Explanations

    specific listing examples

    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
     даже
    -0.82
     useEffect
    -0.81
     дуже
    -0.79
    悼
    -0.79
    моро
    -0.79
    rencia
    -0.75
     Archiproducts
    -0.75
    ilkan
    -0.75
    emptyset
    -0.73
     convento
    -0.73
    POSITIVE LOGITS
     Grou
    0.95
     ####
    0.93
     TripAdvisor
    0.89
     iti
    0.88
    fficient
    0.86
     quiser
    0.84
     ২০১
    0.84
    方才
    0.82
    Option
    0.82
    decay
    0.81
    Activations Density 0.013%

    No Known Activations