© 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. 150634
    Prev
    Next
    INDEX
    Explanations

    section joint :: dirt favorite

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

    while other

    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
    "
    0.48
    "...
    0.44
    '
    0.43
    -
    0.43
     sending
    0.41
     cleaner
    0.40
     tinh
    0.40
    กล
    0.40
     eighteenth
    0.40
     leurs
    0.39
    POSITIVE LOGITS
     Сайт
    0.52
     సీజ
    0.50
    టో
    0.49
    ᙱ
    0.47
    𝙄
    0.47
    𝟭
    0.47
    পাত্র
    0.47
    站点
    0.46
    𓏧
    0.46
    ğa
    0.46
    Activations Density 0.000%

    No Known Activations