© 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. 165528
    Prev
    Next
    INDEX
    Explanations

    posted by

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

    interpretations might

    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
     =
    0.43
     Ос
    0.41
     Gilmore
    0.40
     rightfully
    0.40
     Y
    0.40
     couldn
    0.39
     شركة
    0.39
    دايه
    0.39
     Maj
    0.39
     succeeding
    0.39
    POSITIVE LOGITS
    微生物
    0.52
    萸
    0.51
    医学
    0.49
     বিশ্লেষণ
    0.47
     anvä
    0.46
     নূতন
    0.45
     pesso
    0.44
    વું
    0.44
     Phylogenetic
    0.44
     উদ্বাস্তুদের
    0.44
    Activations Density 0.002%

    No Known Activations