© 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. 89604
    Prev
    Next
    INDEX
    Explanations

    north limit

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

    specifically designed

    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
     Leonid
    0.42
     dünyaya
    0.41
     Honorary
    0.40
    0.40
     zusätzliche
    0.38
     بتوان
    0.38
     ‘
    0.37
    diy
    0.37
     Diaspora
    0.37
     prequel
    0.37
    POSITIVE LOGITS
    ﾝ
    0.52
    extré
    0.51
    Choisissez
    0.49
    哪個
    0.49
    ጬ
    0.46
     אבל
    0.46
    ૢ
    0.45
    だから
    0.45
     በሽታ
    0.45
    बांध
    0.44
    Activations Density 0.003%

    No Known Activations