© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54680
    Prev
    Next
    INDEX
    Explanations

    python code imports

    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_40_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
    UnitTest
    0.48
    UNIT
    0.44
    CMS
    0.44
    
    0.43
    Unit
    0.42
    Choice
    0.40
    Fully
    0.39
    UNITY
    0.39
     asl
    0.38
    SC
    0.38
    POSITIVE LOGITS
     crianças
    0.46
     bambini
    0.45
     widow
    0.42
     बच्चों
    0.40
     children
    0.39
     ос
    0.39
    ೃಷ್ಟ
    0.39
    뜨
    0.38
     Coul
    0.38
     pathological
    0.38
    Activations Density 0.002%

    No Known Activations