© 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. 97823
    Prev
    Next
    INDEX
    Explanations

    service, volunteer, students, games

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

    if you

    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
     多
    0.51
    熒
    0.49
     書
    0.49
     культур
    0.48
     防
    0.47
     合
    0.46
    DEPENDENCIA
    0.45
     ReturnVal
    0.45
     书
    0.44
     會
    0.44
    POSITIVE LOGITS
     calmness
    0.49
     murderers
    0.49
     courting
    0.47
    ق
    0.46
    แต่
    0.46
     দিবস
    0.46
     tranquility
    0.45
     extrême
    0.44
     démont
    0.44
     humiliation
    0.44
    Activations Density 0.000%

    No Known Activations