© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7971
    Prev
    Next
    INDEX
    Explanations

    original ideas or elements

    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_31_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
     ordinarily
    0.74
    ক্ষেত্রে
    0.74
    वीं
    0.73
     usually
    0.71
    কর
    0.69
    樖
    0.69
     noticeable
    0.68
    আমরা
    0.68
     updating
    0.68
    مة
    0.66
    POSITIVE LOGITS
     sin
    0.71
    谅
    0.64
    まま
    0.62
     intent
    0.62
    iaire
    0.60
     свят
    0.60
    ien
    0.57
    ⭐⭐
    0.56
    iawan
    0.56
    พัน
    0.55
    Activations Density 0.057%

    No Known Activations