© 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. 190362
    Prev
    Next
    INDEX
    Explanations

    my customers

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

    orgasm, mission, images, format, BIOS, one

    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
    нем
    0.49
    нь
    0.48
    NOVEMBER
    0.48
    뽁
    0.48
    SERVICIO
    0.47
    쌔
    0.46
    DIST
    0.46
    銨
    0.46
    หย
    0.45
    ць
    0.45
    POSITIVE LOGITS
    éal
    0.50
    writeHead
    0.48
     definitively
    0.48
     noticeably
    0.47
    imgPath
    0.46
     sensitively
    0.46
    apsed
    0.45
    uffix
    0.45
    ugu
    0.44
     elegantly
    0.44
    Activations Density 0.000%

    No Known Activations