© 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. 54935
    Prev
    Next
    INDEX
    Explanations

    Future Technology

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

    cat stares

    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
     slicing
    0.51
    就需要
    0.49
    Յ
    0.46
     ralent
    0.46
     sputtering
    0.46
    บ่ง
    0.45
    ต้
    0.44
    নিজের
    0.43
    ඊ
    0.43
    ก่
    0.43
    POSITIVE LOGITS
     senhores
    0.50
     abandoned
    0.48
    那個
    0.46
     oficialmente
    0.45
     إعادة
    0.45
     оста
    0.44
    茈
    0.43
     agree
    0.42
    closures
    0.42
    agree
    0.42
    Activations Density 0.000%

    No Known Activations