© 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. 226098
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    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
    Ằ
    0.54
    队
    0.49
    HORIZONTAL
    0.48
    createNew
    0.48
    虹
    0.47
    setView
    0.45
     اکبر
    0.44
    恒
    0.44
     י
    0.44
    スタル
    0.44
    POSITIVE LOGITS
     del
    0.49
    icates
    0.44
     খাবারের
    0.44
     Indones
    0.44
     OS
    0.44
     Filipinos
    0.44
     Trustees
    0.44
     जिम्मेदार
    0.43
     অনুমান
    0.43
     Customers
    0.42
    Activations Density 0.004%

    No Known Activations