© 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. 97384
    Prev
    Next
    INDEX
    Explanations

    death or casualty

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

    connecting phrases or reasons

    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
    暝
    0.43
     बुधवार
    0.42
    iedo
    0.40
    idah
    0.40
    🤤
    0.40
    xiety
    0.39
     বুধবার
    0.39
    ወት
    0.39
    monday
    0.39
    !
    0.39
    POSITIVE LOGITS
     kvůli
    0.52
     vanwege
    0.52
     wegen
    0.49
     连接
    0.47
     beiden
    0.45
     infix
    0.45
     owing
    0.44
     keySchedule
    0.44
     hỗ
    0.44
     connect
    0.43
    Activations Density 0.002%

    No Known Activations