© 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. 88366
    Prev
    Next
    INDEX
    Explanations

    written by experts

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

    rules and requirements

    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
    𝘱
    0.55
    c
    0.54
    ंटर
    0.54
    したがって
    0.52
    ο
    0.51
    𝘸
    0.49
     ingin
    0.48
    keras
    0.48
    ε
    0.48
     diseño
    0.47
    POSITIVE LOGITS
     посу
    0.47
     벗
    0.47
    ijden
    0.46
     paws
    0.46
     الشع
    0.46
     صاح
    0.45
     شف
    0.45
     اند
    0.44
    ashes
    0.44
     الوقت
    0.44
    Activations Density 0.001%

    No Known Activations