© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2480
    Prev
    Next
    INDEX
    Explanations

    concepts related to people and social constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    ing
    0.57
    UPDATE
    0.56
     fermentation
    0.52
     उभार
    0.52
    ు
    0.50
    ことに
    0.50
    تم
    0.49
    logging
    0.48
     coagulation
    0.48
     measurements
    0.47
    POSITIVE LOGITS
    yLint
    0.71
     Rush
    0.68
    ﹕
    0.66
     Judicial
    0.66
     等
    0.65
    <unused183>
    0.65
    achron
    0.64
    <unused592>
    0.64
     الارد
    0.63
     Racial
    0.63
    Activations Density 0.000%

    No Known Activations