© 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-65K
    7. 55917
    Prev
    Next
    INDEX
    Explanations

    start of explanation

    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_65k_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
    军队
    0.45
     أنواع
    0.42
    荠
    0.41
     Maritime
    0.41
    攻擊
    0.41
    वे
    0.40
     অস্ত্র
    0.39
     Flights
    0.39
    <unused647>
    0.39
     Informatics
    0.38
    POSITIVE LOGITS
    。
    0.45
     stond
    0.43
     reheat
    0.42
     wok
    0.42
     argon
    0.41
     warto
    0.41
     midsole
    0.40
     that
    0.39
     hold
    0.39
     shale
    0.39
    Activations Density 0.026%

    No Known Activations