© 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. 200121
    Prev
    Next
    INDEX
    Explanations

    seeing and looking at

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

    looking, staring, or gazing

    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
    iverse
    0.50
    ナソニック
    0.41
    тьяна
    0.41
    꿩
    0.40
     discredit
    0.39
    etermined
    0.39
     чтобы
    0.38
    сл
    0.38
    त्याने
    0.38
    த்துள்
    0.38
    POSITIVE LOGITS
     Courier
    0.50
     gaze
    0.48
     gazing
    0.47
     sguardo
    0.46
     ብ
    0.46
     gazed
    0.45
    を見る
    0.44
    眺
    0.44
     stared
    0.44
    addNew
    0.43
    Activations Density 0.001%

    No Known Activations