© 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. 66226
    Prev
    Next
    INDEX
    Explanations

    feel children Lord day what

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

    Mortal Kombat

    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
    Par
    0.50
    ibt
    0.50
    ان
    0.49
    ام
    0.49
    ਬ
    0.49
    an
    0.48
    ittet
    0.48
    ationen
    0.48
    itte
    0.48
    igungen
    0.47
    POSITIVE LOGITS
     TextAlign
    0.55
     Fórmula
    0.53
    ">%
    0.52
     Воло
    0.50
     Đầu
    0.50
    的项目
    0.49
     透
    0.48
     Departament
    0.48
     usada
    0.48
     ModInt
    0.48
    Activations Density 0.000%

    No Known Activations