© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6944
    Prev
    Next
    INDEX
    Explanations

    abstract concepts like religion or education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    0.97
    s
    0.74
    д
    0.71
    ть
    0.71
     Skyscanner
    0.70
    в
    0.66
    ы
    0.65
    ᇁ
    0.63
    oretically
    0.63
    ς
    0.63
    POSITIVE LOGITS
    में
    0.78
     عین
    0.75
    :
    0.72
    ामुळे
    0.72
    带来的
    0.69
    ৪
    0.68
    estry
    0.68
    पीड़न
    0.68
    新たな
    0.68
     والسلام
    0.66
    Activations Density 0.154%

    No Known Activations