© 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. 102394
    Prev
    Next
    INDEX
    Explanations

    places and origins

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

    English spelling variations

    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
     本当
    0.50
     Gomes
    0.47
     Would
    0.45
     程序
    0.45
     봐
    0.44
     じゃ
    0.44
     だ
    0.44
     因為
    0.44
     しかし
    0.43
     secured
    0.43
    POSITIVE LOGITS
    anterior
    0.51
    лих
    0.49
     város
    0.48
     logarithmic
    0.46
     fusible
    0.46
     entier
    0.45
     STADT
    0.45
    awie
    0.45
    ayin
    0.45
    extrem
    0.45
    Activations Density 0.001%

    No Known Activations