© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    ครับ:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    tt
    3.10
    tanto
    3.09
    ti
    3.08
    tan
    3.05
    此之外
    2.91
    袤
    2.89
    tout
    2.72
    thead
    2.65
    tri
    2.64
    `${
    2.60
    POSITIVE LOGITS
    urized
    2.59
    欠
    2.56
    rifice
    2.50
    oulders
    2.48
    ियों
    2.47
     جت
    2.45
    ณฑ
    2.45
    CoA
    2.45
     ',');
    2.42
    日程
    2.41
    Activations Density 0.021%

    No Known Activations