© 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. 86955
    Prev
    Next
    INDEX
    Explanations

    mummies and mummification

    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
     toneladas
    0.71
    هم
    0.68
    ເມ
    0.62
    ட்சத்திர
    0.62
    侩
    0.62
     Trabal
    0.61
    ກ
    0.61
     отказа
    0.60
    ঘ্র
    0.60
    listItem
    0.59
    POSITIVE LOGITS
     C
    0.63
    in
    0.50
    Consistency
    0.50
    ings
    0.48
     conversion
    0.48
    informatics
    0.48
    m
    0.47
     {
    0.46
    ür
    0.46
    processing
    0.46
    Activations Density 0.001%

    No Known Activations