© 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. 80642
    Prev
    Next
    INDEX
    Explanations

    driver updates or reach out

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

    AI/Machine Learning concepts

    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
     アウトドア
    0.46
    ਧੀ
    0.43
    animal
    0.41
     aquatic
    0.41
    カ
    0.40
    anned
    0.39
    楽しい
    0.39
    ac
    0.39
    verbal
    0.39
    チ
    0.39
    POSITIVE LOGITS
     Loader
    0.54
    硕
    0.48
     Layout
    0.46
     একইভাবে
    0.45
    轨
    0.45
    场的
    0.44
    愔
    0.44
    在这
    0.44
     পূর্বে
    0.43
     时
    0.43
    Activations Density 0.001%

    No Known Activations