© 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. 181641
    Prev
    Next
    INDEX
    Explanations

    style, usually, often

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

    energy grids charging connection

    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
    ת
    0.55
    RELATIVE
    0.50
    விட்டால்
    0.48
    اتی
    0.47
     irritating
    0.47
     adjunct
    0.46
    াঙ্গ
    0.46
    莯
    0.46
    ्रा
    0.45
    ADIUM
    0.45
    POSITIVE LOGITS
     रहकर
    0.54
    ോക
    0.48
    bei
    0.45
    inta
    0.45
    Fax
    0.44
    roma
    0.43
    ringen
    0.43
     заседа
    0.43
    run
    0.43
    Run
    0.43
    Activations Density 0.000%

    No Known Activations