© 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. 206282
    Prev
    Next
    INDEX
    Explanations

    extremely grateful, potential members, fairly regular

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

    word patterns

    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
     Trees
    0.50
     অ্য
    0.47
     Modem
    0.46
    Trees
    0.46
     ভূপ
    0.46
    SH
    0.45
     Bedrooms
    0.45
    $
    0.45
     Rtl
    0.45
     公司
    0.45
    POSITIVE LOGITS
    し
    0.48
    じん
    0.46
    asone
    0.46
    บูร
    0.46
    ਡੇ
    0.46
    اهده
    0.45
    した
    0.44
    iais
    0.44
     ببین
    0.44
    जेट
    0.44
    Activations Density 0.000%

    No Known Activations