© 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. 7684
    Prev
    Next
    INDEX
    Explanations

    approximately or nearly

    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
    カイブ
    0.60
    トゥーン
    0.59
     []);
    0.57
    primir
    0.57
     japonesa
    0.57
     otomatis
    0.57
     விதிக்க
    0.57
    סק
    0.56
     worldRank
    0.56
    ዋል።
    0.56
    POSITIVE LOGITS
     years
    0.67
    约
    0.63
    nearly
    0.60
    approx
    0.60
     nearly
    0.59
    years
    0.57
     लगभग
    0.55
    Approximately
    0.55
     approximately
    0.54
     approx
    0.54
    Activations Density 0.006%

    No Known Activations