© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 13110
    Prev
    Next
    INDEX
    Explanations

    top N rankings

    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
    ↵
    0.77
    =
    0.76
     with
    0.70
    "
    0.67
    .)
    0.67
    {
    0.66
    :
    0.66
    га
    0.65
    з
    0.64
    /
    0.63
    POSITIVE LOGITS
    ième
    0.68
    érence
    0.66
     mRNAs
    0.65
     świata
    0.64
     советы
    0.64
    mér
    0.63
    chés
    0.62
     自己
    0.62
    elolaan
    0.62
    érences
    0.61
    Activations Density 0.059%

    No Known Activations