© 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. 210564
    Prev
    Next
    INDEX
    Explanations

    linking phrases or ideas

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

    your potential cause or community

    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
    こんにちは
    0.46
     lattices
    0.46
     laag
    0.43
     ബാല
    0.42
     baseman
    0.42
     লিখেছেন
    0.41
     bygg
    0.41
    ¢
    0.41
    processor
    0.41
     medlem
    0.41
    POSITIVE LOGITS
    ıy
    0.54
     सांस
    0.46
     অবশেষে
    0.45
    owymi
    0.44
    ାନ
    0.42
     zape
    0.42
     अपेक्षित
    0.42
     LUT
    0.41
    indul
    0.40
    estes
    0.40
    Activations Density 0.000%

    No Known Activations