© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83977
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meisten
    0.50
    س
    0.48
    ς
    0.48
    s
    0.47
     сім
    0.44
     fried
    0.44
    را
    0.44
    شو
    0.42
    니다
    0.40
     spam
    0.40
    POSITIVE LOGITS
     ත
    0.50
     использованием
    0.49
    ⌞
    0.48
     વડે
    0.45
     ಕಾರ್ಯ
    0.45
    IdleSync
    0.44
     adapts
    0.44
    <unused2121>
    0.43
    <unused2199>
    0.43
    !()
    0.43
    Activations Density 0.002%

    No Known Activations