© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34114
    Prev
    Next
    INDEX
    Explanations

    decimal point

    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
     Phát
    0.65
    ংস
    0.63
    marshalO
    0.61
     Feuilles
    0.61
     春
    0.60
     بأن
    0.60
     ممكن
    0.59
    不同的
    0.58
    ينا
    0.57
    feo
    0.57
    POSITIVE LOGITS
    І
    0.69
    ک
    0.63
    oyle
    0.60
    ক
    0.59
    UNG
    0.58
    ミ
    0.58
    स्ट
    0.57
    وی
    0.55
    iob
    0.55
    ii
    0.55
    Activations Density 0.001%

    No Known Activations