© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116694
    Prev
    Next
    INDEX
    Explanations

    Modus Ponens Toll Layout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=
    0.50
     Radio
    0.50
     внутри
    0.50
    封装
    0.49
     radio
    0.49
     WHEN
    0.47
     двадцать
    0.47
     содержа
    0.47
     seura
    0.46
     закреп
    0.46
    POSITIVE LOGITS
    مرين
    0.54
    訌
    0.51
    amor
    0.48
     التج
    0.47
    experimental
    0.47
    rester
    0.47
    ampton
    0.45
    fton
    0.45
    ករណ៍
    0.44
    expectation
    0.44
    Activations Density 0.001%

    No Known Activations