© 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. 31920
    Prev
    Next
    INDEX
    Explanations

    times, SKUs, and PDFs

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

    protocols 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
     YOU
    0.57
    ς
    0.52
     WASHINGTON
    0.51
     پیسہ
    0.50
     DAI
    0.50
    °)
    0.49
    și
    0.49
     GAN
    0.49
    lEdit
    0.49
    ifai
    0.49
    POSITIVE LOGITS
     at
    0.63
    为
    0.59
    to
    0.56
     Apples
    0.54
    ਾ
    0.54
    the
    0.54
    на
    0.52
    ER
    0.52
    ا
    0.50
    不妨
    0.50
    Activations Density 0.042%

    No Known Activations