© 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. 33027
    Prev
    Next
    INDEX
    Explanations

    open source

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

    cube engine, compiling systems

    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
     下さい
    0.49
    FUL
    0.48
    meid
    0.46
     болот
    0.46
    澱
    0.45
     বাতাস
    0.45
     ANOTHER
    0.44
     RECEIVED
    0.44
    ﻢ
    0.43
     ねえ
    0.43
    POSITIVE LOGITS
    สำหรับ
    0.52
    反对
    0.47
     परिवर्त
    0.46
     élarg
    0.45
     چار
    0.44
     Writings
    0.44
     City
    0.43
     পারবে
    0.43
     sépt
    0.43
    项目
    0.43
    Activations Density 0.000%

    No Known Activations