© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    shape and data type

    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
    ション
    0.45
    REDIR
    0.43
    ర్‌
    0.41
    RENGTH
    0.39
    也不能
    0.39
    引入
    0.39
     ற
    0.39
     کړ
    0.38
     লিখিতে
    0.38
     પારિજા
    0.38
    POSITIVE LOGITS
     brutal
    0.45
     parades
    0.44
     flapping
    0.43
     brutally
    0.41
     fucking
    0.40
     indes
    0.39
    battery
    0.38
     distribuição
    0.38
     fucked
    0.38
     ബാറ്ററി
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.