© 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. 112763
    Prev
    Next
    INDEX
    Explanations

    services or Site

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

    basic method or core component

    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
    初めて
    0.51
    접
    0.50
    家中
    0.49
    웍
    0.49
    िंग
    0.48
    었다
    0.48
    их
    0.47
    윅
    0.47
    튿
    0.47
     battling
    0.46
    POSITIVE LOGITS
    yun
    0.53
     monoton
    0.49
     fol
    0.48
     Pa
    0.47
    +-
    0.46
     for
    0.45
    står
    0.45
    ='\
    0.45
     TBS
    0.45
     T
    0.45
    Activations Density 0.000%

    No Known Activations