© 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. 124282
    Prev
    Next
    INDEX
    Explanations

    Etymology, him, shop, shipment

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

    resist the urge

    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
     流
    0.47
    ELS
    0.45
    xtime
    0.45
    体制
    0.44
    ESI
    0.43
    стане
    0.43
    ANDS
    0.43
    原生
    0.43
    ባቸው
    0.42
    ارين
    0.42
    POSITIVE LOGITS
    ");
    0.48
     Shoe
    0.47
     SHOP
    0.47
     anggota
    0.46
     Мини
    0.46
     Candida
    0.46
     Sherlock
    0.45
     unele
    0.45
     that
    0.45
    ică
    0.45
    Activations Density 0.001%

    No Known Activations