© 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. 106667
    Prev
    Next
    INDEX
    Explanations

    payment usingparking prices

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

    finding sales, Character Creation

    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
     ਘ
    0.50
     casket
    0.45
    ικός
    0.44
    hours
    0.43
     pervasive
    0.42
     মর্টার
    0.41
     प्रकर
    0.41
    ها
    0.40
    最初の
    0.40
     harnessing
    0.40
    POSITIVE LOGITS
    녔
    0.49
    ulik
    0.49
    Bibli
    0.49
    0
    0.48
    毕业
    0.47
    Chứng
    0.46
     Refs
    0.45
    otec
    0.44
    otele
    0.43
    oling
    0.43
    Activations Density 0.002%

    No Known Activations