© 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. 88243
    Prev
    Next
    INDEX
    Explanations

    email or hyperlinks

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

    print statements

    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
    ני
    0.52
    ต้า
    0.51
    ве
    0.49
     เห็น
    0.49
     എന്റെ
    0.49
    ฯ
    0.48
    եր
    0.48
    ล
    0.47
     예약
    0.47
    热闹
    0.46
    POSITIVE LOGITS
    0.49
    apon
    0.47
     contin
    0.47
    utch
    0.45
    until
    0.45
     screen
    0.45
    ottle
    0.45
     system
    0.44
     tempr
    0.43
     funcionando
    0.43
    Activations Density 0.001%

    No Known Activations