© 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. 179436
    Prev
    Next
    INDEX
    Explanations

    casino tickets, slot machines, jar tickets

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

    spending, taxes, pipelines

    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
     忄
    0.54
    ды
    0.52
    所有的
    0.50
    想法
    0.48
    ле
    0.48
     декора
    0.47
    亮
    0.47
    allItems
    0.46
    و
    0.46
     adição
    0.46
    POSITIVE LOGITS
    ained
    0.54
    ämän
    0.46
    Օ
    0.46
    steuer
    0.45
    Ꮮ
    0.43
    मधील
    0.42
    ucle
    0.42
    Pix
    0.42
     Pä
    0.42
    apa
    0.41
    Activations Density 0.001%

    No Known Activations