© 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. 88454
    Prev
    Next
    INDEX
    Explanations

    detection of

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

    recommended experience

    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
    0.62
     Brigham
    0.49
     name
    0.48
    wordpress
    0.47
    is
    0.46
    子
    0.46
    ad
    0.45
     Beaumont
    0.44
    u
    0.44
    id
    0.43
    POSITIVE LOGITS
     வால்பேப்பர்
    0.52
    ম্ত
    0.50
    VIDENCE
    0.49
     تجویز
    0.48
    TARIFF
    0.48
    MAGNET
    0.48
     वित्त
    0.47
     надо
    0.47
     была
    0.46
     नशे
    0.46
    Activations Density 0.001%

    No Known Activations