© 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. 24275
    Prev
    Next
    INDEX
    Explanations

    opposing estate regeneration

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

    drone patrols and incursions

    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
    ッカー
    0.45
    saver
    0.45
    浏览器
    0.45
    ásticos
    0.45
    alertDialog
    0.45
    (',',
    0.43
    🌝
    0.43
     chúc
    0.42
    お願いします
    0.42
    긋
    0.42
    POSITIVE LOGITS
     مُ
    0.44
     Stake
    0.42
     ပါ
    0.40
     Diverse
    0.39
     Heli
    0.39
     مدينه
    0.39
     December
    0.38
     TCE
    0.38
     crumbling
    0.38
     diverse
    0.37
    Activations Density 0.000%

    No Known Activations