© 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. 65045
    Prev
    Next
    INDEX
    Explanations

    institution or establishment

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

    responsible for, focusing on, subscribing to

    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
     Jerry
    0.44
     airlines
    0.43
     variants
    0.41
    <0xE3>
    0.40
    ்துறை
    0.40
    ers
    0.40
     oni
    0.39
     Nand
    0.39
     V
    0.39
     sources
    0.39
    POSITIVE LOGITS
    寵
    0.54
     мероприя
    0.51
     учре
    0.50
     заседа
    0.49
     школова
    0.49
     навчання
    0.49
     설립
    0.49
     miejscu
    0.48
    ItemStack
    0.47
     marries
    0.47
    Activations Density 0.000%

    No Known Activations