© 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. 163995
    Prev
    Next
    INDEX
    Explanations

    your order, fleet went, active parts, Panama Canal

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

    word following word

    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
    찡
    0.52
    骧
    0.50
    蹩
    0.48
    称
    0.48
     لقب
    0.47
    顰
    0.47
     الجميع
    0.46
     Appointments
    0.45
     Physician
    0.44
    跛
    0.44
    POSITIVE LOGITS
     ਅਤੇ
    0.54
     classrooms
    0.53
    CubeSize
    0.52
     pollutants
    0.52
     aerosols
    0.52
    電気
    0.51
     asteroids
    0.51
    accharides
    0.51
     playgrounds
    0.50
     niños
    0.50
    Activations Density 0.001%

    No Known Activations