© 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. 210993
    Prev
    Next
    INDEX
    Explanations

    Unix server

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

    problems, Center, Sound, athletic, battlefield, Caso

    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
    श्वर
    0.50
     murdered
    0.47
    .
    0.47
    Limitations
    0.44
     comedian
    0.44
     erinn
    0.44
     sitt
    0.44
     comedians
    0.44
     sim
    0.43
    回り
    0.43
    POSITIVE LOGITS
     후보
    0.49
     이슈
    0.46
    ിലി
    0.46
    落实
    0.45
    semanticweb
    0.45
     currentDate
    0.45
     alttext
    0.44
     국
    0.44
    ཎ
    0.44
    许可证
    0.43
    Activations Density 0.001%

    No Known Activations