© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115062
    Prev
    Next
    INDEX
    Explanations

    foreign words or characters

    np_acts-logits-general · gemini-2.5-flash-lite

    distributions, revenue, ratings, computing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    namely
    0.43
    r
    0.42
    whose
    0.41
    AND
    0.40
    t
    0.39
    包含
    0.39
    自身の
    0.39
    ussels
    0.39
     sirf
    0.39
     (
    0.38
    POSITIVE LOGITS
    嗥
    0.50
     difíciles
    0.49
     difficol
    0.49
    !।
    0.48
     جوړونکي
    0.47
     แน
    0.47
     길
    0.47
     haunting
    0.47
    ฉัน
    0.47
     закін
    0.46
    Activations Density 0.001%

    No Known Activations