© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    sections with headings

    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
    это
    0.37
    Ро
    0.37
    С
    0.37
    й
    0.37
    у
    0.35
    นี่
    0.34
     этот
    0.33
     този
    0.33
    uelos
    0.33
    这个
    0.33
    POSITIVE LOGITS
     bronch
    0.33
     radiographic
    0.33
     magnetometer
    0.33
     শা
    0.32
     সম্পাদকীয়
    0.32
    嗶
    0.32
     ಹೊಂದಿ
    0.31
     delineation
    0.31
     declaraciones
    0.31
     Bankr
    0.31
    Activations Density 0.006%

    No Known Activations