© 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. 74142
    Prev
    Next
    INDEX
    Explanations

    USB port

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

    data management and security

    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
    ピッ
    0.48
    olas
    0.45
    сім
    0.44
    碰
    0.44
    넝
    0.44
    __'
    0.44
    उसके
    0.42
    сцю
    0.42
    жы
    0.42
     workmanship
    0.42
    POSITIVE LOGITS
     これらの
    0.47
    ി
    0.42
     al
    0.42
     सामाजिक
    0.41
     सत्य
    0.41
     Analytics
    0.41
    ۳
    0.41
     ४
    0.41
     FileNotFound
    0.41
     Individuals
    0.41
    Activations Density 0.000%

    No Known Activations