© 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. 225483
    Prev
    Next
    INDEX
    Explanations

    Goff scored, remember point

    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
    我們
    0.55
    台灣
    0.53
    瓏
    0.52
    不斷
    0.50
    綜
    0.49
    處
    0.47
     delineation
    0.46
     單
    0.46
    檔
    0.46
     Năm
    0.46
    POSITIVE LOGITS
     madd
    0.47
     بازیکن
    0.47
     keuangan
    0.45
     senyawa
    0.44
     माधव
    0.44
     médicas
    0.43
     üzere
    0.43
    bats
    0.43
     selamat
    0.42
     batalla
    0.42
    Activations Density 0.000%

    No Known Activations