© 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. 156518
    Prev
    Next
    INDEX
    Explanations

    system specifications and descriptions

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

    Sorites paradox, car, flip-flop

    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
    너
    0.51
    吸收
    0.49
    Lady
    0.49
    ilians
    0.49
    After
    0.48
    Finally
    0.48
    率
    0.47
    记忆
    0.47
    Then
    0.47
    伀
    0.46
    POSITIVE LOGITS
     espacios
    0.50
     автомобиль
    0.49
    🖥
    0.47
     hatal
    0.47
     ワイド
    0.47
    🛵
    0.45
    ່ມ
    0.45
     billowing
    0.45
    ँव
    0.45
     tomography
    0.44
    Activations Density 0.000%

    No Known Activations