© 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. 136348
    Prev
    Next
    INDEX
    Explanations

    the/a/your/Global + specific noun

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

    quality, system, file, Flask, MD

    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
    acher
    0.50
    үүн
    0.49
    🧇
    0.46
     இந்ந
    0.45
    Peach
    0.44
    ämä
    0.44
     cushioned
    0.44
    ạm
    0.43
    ަމ
    0.43
    knie
    0.43
    POSITIVE LOGITS
     Quels
    0.48
    的な
    0.45
     Mino
    0.45
     Kend
    0.44
    적
    0.44
    Για
    0.43
    󰀄
    0.43
     Erik
    0.42
     Morse
    0.41
    桝
    0.41
    Activations Density 0.000%

    No Known Activations