© 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. 212770
    Prev
    Next
    INDEX
    Explanations

    a sequence followed by `of` or `your`

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

    SMART Data, Pulse, globally,embedded

    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
    reservation
    0.46
    rc
    0.43
    strings
    0.43
    个数
    0.43
     该
    0.42
     reservation
    0.42
     grpc
    0.42
    rak
    0.42
     Hz
    0.41
    ωσ
    0.41
    POSITIVE LOGITS
     ماد
    0.51
    leyici
    0.51
     yönet
    0.50
    leges
    0.48
     kleine
    0.48
    ierend
    0.48
     करियर
    0.48
     आयुष्मान
    0.48
     முறையில்
    0.47
    嫖
    0.47
    Activations Density 0.001%

    No Known Activations