© 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. 222630
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    foundational awareness and perception

    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
    アナ
    0.57
    2
    0.57
    ונ
    0.55
     TESTS
    0.55
    ע
    0.55
    ।.
    0.53
     Warnings
    0.52
    ।
    0.52
     Burial
    0.52
     NOTES
    0.51
    POSITIVE LOGITS
    ü
    0.60
     І
    0.57
     conos
    0.51
    ст
    0.49
    知道
    0.47
    ę
    0.47
    此刻
    0.47
     sobretudo
    0.47
    ля
    0.47
    ază
    0.46
    Activations Density 0.000%

    No Known Activations