© 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. 31439
    Prev
    Next
    INDEX
    Explanations

    local regulations and permits

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

    function call

    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
    0.46
    </h4>
    0.41
     Contempor
    0.40
     ascertain
    0.40
     epitome
    0.39
     isolates
    0.38
     indict
    0.38
    perme
    0.38
    reminder
    0.38
    <bos>
    0.38
    POSITIVE LOGITS
     функції
    0.48
    Quick
    0.47
    龴
    0.47
    包括
    0.47
    购物车
    0.46
    瑢
    0.46
    Savings
    0.46
    нная
    0.45
     функ
    0.45
    वेलकम
    0.45
    Activations Density 0.000%

    No Known Activations