© 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. 143597
    Prev
    Next
    INDEX
    Explanations

    old texts and numbers

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

    fallacy of popularity

    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
    たる
    0.54
    ట్స్‌
    0.50
    詞
    0.48
    斯的
    0.47
    గ్
    0.47
     chock
    0.46
    ضاف
    0.45
    adne
    0.45
    則是
    0.45
    సుకోవ
    0.44
    POSITIVE LOGITS
     certaines
    0.55
     certains
    0.54
     দর্শকদের
    0.53
     determinadas
    0.50
    getCQL
    0.49
     フランス
    0.49
     seules
    0.48
     pregi
    0.48
     ﺍ
    0.47
     entraî
    0.46
    Activations Density 0.000%

    No Known Activations