© 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. 126963
    Prev
    Next
    INDEX
    Explanations

    dim DS / ID

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

    const keyword in C++

    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
     governing
    0.45
     EQUIPMENT
    0.45
     ENGINE
    0.44
    ή
    0.41
     train
    0.39
     svého
    0.39
     NAMES
    0.38
     engine
    0.38
    ৫
    0.38
     welding
    0.38
    POSITIVE LOGITS
     일반
    0.50
     विटामिन
    0.46
     효과
    0.46
     벡터
    0.46
     ssize
    0.45
     비용
    0.45
     전혀
    0.45
     दर्शक
    0.44
     كيفية
    0.44
     낮은
    0.43
    Activations Density 0.000%

    No Known Activations