© 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. 22615
    Prev
    Next
    INDEX
    Explanations

    choosing the first

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

    fft, ∪, published

    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
     多く
    0.44
    )==
    0.43
     BUILD
    0.43
     भला
    0.43
     enjo
    0.41
    羸
    0.41
     रेगु
    0.41
     mobilise
    0.41
    𝐧
    0.41
     divert
    0.41
    POSITIVE LOGITS
    合适
    0.51
    第一
    0.47
     odpowied
    0.46
    俄罗斯
    0.45
    碰撞
    0.45
    结果
    0.44
    结束后
    0.44
    出发
    0.44
    比亚
    0.43
    选取
    0.43
    Activations Density 0.000%

    No Known Activations