© 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. 131438
    Prev
    Next
    INDEX
    Explanations

    week, weekly, or dates

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

    Winckelmann, Franklin, scientists

    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
    ストレ
    0.51
     نرم
    0.47
    くまで
    0.47
    تها
    0.47
    كد
    0.46
    ْن
    0.46
    禀
    0.46
    TOKEN
    0.46
    COT
    0.46
    Carte
    0.46
    POSITIVE LOGITS
     Urology
    0.50
     conceptually
    0.47
     Alaska
    0.45
     computationally
    0.45
    opolar
    0.44
    week
    0.43
    iyi
    0.43
     juxtap
    0.43
    weekly
    0.43
    Ǻ
    0.43
    Activations Density 0.000%

    No Known Activations