© 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. 219621
    Prev
    Next
    INDEX
    Explanations

    at followed by a noun or place

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

    at

    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
    內容
    0.41
    ようです
    0.39
    ورش
    0.39
    蝴
    0.39
    椪
    0.38
    缪
    0.38
    臆
    0.37
     repercussions
    0.37
    大陸
    0.37
     %)
    0.36
    POSITIVE LOGITS
     at
    0.51
    ivation
    0.49
    from
    0.48
     Tại
    0.48
     from
    0.46
     tại
    0.44
     ตั้ง
    0.44
    ivities
    0.44
    ition
    0.43
     atac
    0.43
    Activations Density 0.044%

    No Known Activations