© 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. 58644
    Prev
    Next
    INDEX
    Explanations

    your initial

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

    visual content scheduling

    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
    ካት
    0.53
     컴퓨
    0.51
     रिक्वायरमेंट
    0.51
    ชัน
    0.50
    语言
    0.50
    нём
    0.49
     医学
    0.48
    ᵐ
    0.48
    ylmethylsulfanyl
    0.48
    Language
    0.47
    POSITIVE LOGITS
     get
    0.54
     buy
    0.52
     onde
    0.51
     protect
    0.50
     honda
    0.50
     o
    0.49
     execute
    0.48
     ideology
    0.47
    o
    0.47
     take
    0.47
    Activations Density 0.000%

    No Known Activations