© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6914
    Prev
    Next
    INDEX
    Explanations

    Log transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    и
    0.57
    的的
    0.55
    А
    0.55
     ഐ
    0.55
     factorizar
    0.55
    WZ
    0.54
    ༞
    0.54
    <0xF4>
    0.52
    Та
    0.52
    siehe
    0.52
    POSITIVE LOGITS
     HIM
    0.61
     சேர்ந்த
    0.60
     other
    0.55
     anderes
    0.55
     Tomas
    0.53
     artificially
    0.53
     whack
    0.52
    柅
    0.52
     phil
    0.52
    ቹን
    0.52
    Activations Density 0.779%

    No Known Activations