© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144932
    Prev
    Next
    INDEX
    Explanations

    initialization with zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilización
    0.58
     admisión
    0.58
    ட்க
    0.56
     escucha
    0.56
    ﺪ
    0.56
     ک
    0.55
    щих
    0.54
    ک
    0.54
     movilidad
    0.52
    ց
    0.52
    POSITIVE LOGITS
    ten
    0.70
    ta
    0.61
    tag
    0.58
    m
    0.58
    తో
    0.58
    tena
    0.58
    mers
    0.57
    nok
    0.57
    tk
    0.57
    baka
    0.57
    Activations Density 0.001%

    No Known Activations