© 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. 223810
    Prev
    Next
    INDEX
    Explanations

    be visiting

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

    apply early

    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
     Ports
    0.50
     Blades
    0.48
     Technologies
    0.48
    恼
    0.47
    Shroud
    0.47
    乔
    0.45
     Automation
    0.44
     Ehm
    0.44
    远程
    0.44
     Routing
    0.44
    POSITIVE LOGITS
    家に
    0.52
    е
    0.50
    ир
    0.49
    о
    0.48
    виа
    0.47
    に
    0.47
    その
    0.47
    ா
    0.46
    ற்று
    0.46
    して
    0.45
    Activations Density 0.000%

    No Known Activations