© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10594
    Prev
    Next
    INDEX
    Explanations

    Werner, Tur, Eric

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

    turkey, turmeric, lean proteins

    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_40_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
    ेशनों
    0.43
    ]+"
    0.41
    ளாவ
    0.40
     feste
    0.39
    स्ट
    0.39
     setContentView
    0.39
    gé
    0.39
    lois
    0.39
    {@
    0.38
     turn
    0.38
    POSITIVE LOGITS
    ניין
    0.61
    בוד
    0.55
     מע
    0.44
     圆
    0.43
    בודה
    0.42
     செய்ய
    0.41
     круг
    0.41
    圆
    0.40
     یار
    0.39
     叶
    0.39
    Activations Density 0.030%

    No Known Activations