© 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. 106675
    Prev
    Next
    INDEX
    Explanations

    under heaven

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

    shared experiences and relationships

    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
     家
    0.56
    doesn
    0.49
    يب
    0.49
     wob
    0.49
     olmadığını
    0.48
    |=\
    0.48
     tirelessly
    0.48
    &&(
    0.48
    =-
    0.48
    =\
    0.47
    POSITIVE LOGITS
     Abyss
    0.54
     Ab
    0.52
     Up
    0.52
     Troll
    0.48
     Padua
    0.48
     ترقی
    0.47
     Hamburg
    0.47
     Diagram
    0.46
     Post
    0.46
     Tarant
    0.46
    Activations Density 0.000%

    No Known Activations