© 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. 83977
    Prev
    Next
    INDEX
    Explanations

    robbers discovered

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

    creating instances, tracking objects

    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
     meisten
    0.50
    س
    0.50
    s
    0.48
    را
    0.47
    ς
    0.46
    রা
    0.44
    شو
    0.44
     Liberty
    0.43
    니다
    0.43
    2
    0.43
    POSITIVE LOGITS
     использованием
    0.55
    ⌞
    0.48
     ත
    0.47
     修改
    0.47
     등의
    0.47
     adapts
    0.47
     ಕಾರ್ಯ
    0.46
     વડે
    0.46
     achieves
    0.45
     නව
    0.45
    Activations Density 0.001%

    No Known Activations