© 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. 11214
    Prev
    Next
    INDEX
    Explanations

    ROS components and streaming

    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
    ন্দরী
    3.24
    ::$
    3.03
    ี่ป
    2.88
    濡
    2.72
     Enth
    2.69
    cat
    2.68
    cules
    2.58
    globalMap
    2.53
    নে
    2.52
    SPIR
    2.51
    POSITIVE LOGITS
    ﺎ
    3.38
    ीट
    3.32
    ۰
    3.12
    ్
    3.06
    uix
    2.98
    e
    2.87
    o
    2.87
    eyJ
    2.85
    ಿ
    2.82
    ો
    2.81
    Activations Density 0.021%

    No Known Activations