© 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. 84579
    Prev
    Next
    INDEX
    Explanations

    details about China

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

    user prompts

    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
    ъ
    0.57
    летний
    0.53
    ни
    0.53
    ну
    0.50
     осмо
    0.50
    ere
    0.48
    ч
    0.48
    лет
    0.48
    ю
    0.48
    ц
    0.48
    POSITIVE LOGITS
     overfitting
    0.45
     tại
    0.45
     Offshore
    0.44
     interprets
    0.43
     Amplitude
    0.43
     پاس
    0.42
     SONG
    0.42
     passwords
    0.41
     sélectionnés
    0.41
     Select
    0.40
    Activations Density 0.001%

    No Known Activations