© 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. 44723
    Prev
    Next
    INDEX
    Explanations

    pre-packaged

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

    software, Messenger, Bots, SDK

    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
    tif
    0.49
    detect
    0.48
    ाय
    0.47
    nc
    0.46
    u
    0.46
    コ
    0.45
    difficult
    0.45
     complicating
    0.45
    ла
    0.44
     complications
    0.44
    POSITIVE LOGITS
    相关的
    0.49
     Lp
    0.49
     sulla
    0.48
    樯
    0.47
    行为
    0.45
    橹
    0.45
     denna
    0.44
     håller
    0.44
    是一个
    0.44
     Bauern
    0.44
    Activations Density 0.000%

    No Known Activations