© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79711
    Prev
    Next
    INDEX
    Explanations

    services and products

    np_acts-logits-general · gemini-2.5-flash-lite

    AC/DC electricity and converters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Floor
    0.52
     率
    0.52
    (""))
    0.49
     व्यक्तित्व
    0.48
    Activation
    0.48
     นิ
    0.48
    燊
    0.48
    Automation
    0.47
    Colors
    0.46
    merksamkeit
    0.46
    POSITIVE LOGITS
    t
    0.55
     supportive
    0.52
     suspected
    0.50
     turbine
    0.49
    ब्बे
    0.49
     diseased
    0.48
     westbound
    0.47
     healthy
    0.46
     vitro
    0.46
     curb
    0.46
    Activations Density 0.002%

    No Known Activations