© 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. 242285
    Prev
    Next
    INDEX
    Explanations

    expanding quality renting production

    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
    SER
    0.51
    Кон
    0.47
    Кор
    0.46
    รีย
    0.46
    ДО
    0.45
    コン
    0.45
    Сер
    0.45
    ル
    0.44
    ЛИ
    0.44
    ೂರ
    0.44
    POSITIVE LOGITS
    uée
    0.50
     Payable
    0.49
     Panchayat
    0.48
     Salvation
    0.47
     다섯
    0.47
    hetto
    0.45
    ville
    0.45
     Katha
    0.45
     pente
    0.44
     لكرة
    0.44
    Activations Density 0.001%

    No Known Activations