© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84539
    Prev
    Next
    INDEX
    Explanations

    confirm, accuracy, industry, historical, training

    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
    未
    0.43
    家伙
    0.43
    Armed
    0.43
    哪个
    0.42
     armed
    0.40
     brains
    0.39
    ভাল
    0.38
    стями
    0.38
    ման
    0.38
     programs
    0.37
    POSITIVE LOGITS
    .}
    0.58
     incluem
    0.50
    ंनी
    0.50
     वसूल
    0.49
     која
    0.49
     koja
    0.48
     abh
    0.48
     मिळ
    0.47
     दिसते
    0.47
    historical
    0.47
    Activations Density 0.004%

    No Known Activations