© 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. 46663
    Prev
    Next
    INDEX
    Explanations

    assumption that, apt-, basis of

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

    information and status lists

    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
    ):
    0.45
     corporate
    0.41
    corporate
    0.40
    ({
    0.39
    ]:
    0.39
    比如
    0.39
    owane
    0.39
    wheeled
    0.39
    df
    0.38
    ords
    0.38
    POSITIVE LOGITS
    glRaster
    0.48
    amasını
    0.48
     произведение
    0.47
     manfaat
    0.46
    ответ
    0.46
    ೩
    0.46
    ೊಳ
    0.46
    𒉈
    0.45
    ması
    0.45
     harapan
    0.45
    Activations Density 0.000%

    No Known Activations