© 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. 62201
    Prev
    Next
    INDEX
    Explanations

    Long may this winter

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

    TL;DR or TL'DR

    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
    叓
    0.56
    ങ്ക്
    0.55
    മ്പ്
    0.52
    硣
    0.50
    ന്യാ
    0.50
    뉸
    0.49
    资讯
    0.49
    卟
    0.49
    τας
    0.48
    与
    0.48
    POSITIVE LOGITS
    desc
    0.49
    xiang
    0.46
     sleepy
    0.45
    ded
    0.45
    dish
    0.44
     chevron
    0.43
     spes
    0.43
     hexa
    0.43
    cac
    0.43
    dichlor
    0.43
    Activations Density 0.001%

    No Known Activations