© 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. 109834
    Prev
    Next
    INDEX
    Explanations

    hand satisfaction child Rich

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

    contrast or exception

    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
    芢
    0.47
    lmfit
    0.45
    iped
    0.44
    Subview
    0.44
    months
    0.43
    pagina
    0.42
    itaan
    0.42
     Dutchman
    0.42
    uhi
    0.42
    languageTag
    0.42
    POSITIVE LOGITS
    では
    0.45
    時代
    0.45
     Послед
    0.44
    一家
    0.43
     接
    0.43
     outperforms
    0.42
     nowadays
    0.42
     camar
    0.42
    ではありません
    0.42
     ESPE
    0.42
    Activations Density 0.000%

    No Known Activations