© 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. 97019
    Prev
    Next
    INDEX
    Explanations

    messages from, he believed, rail car

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

    different densities and sizes

    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
    鍘
    0.48
    ियाणा
    0.47
     പുതിയ
    0.46
    梼
    0.46
     κάτι
    0.46
    Бу
    0.46
     νέ
    0.45
     οικονομ
    0.45
    რი
    0.43
     Пі
    0.43
    POSITIVE LOGITS
     exemplu
    0.50
    服用
    0.49
     sofern
    0.47
    -
    0.46
     overexpression
    0.46
     labios
    0.44
    ‐
    0.43
    وكان
    0.43
     validated
    0.42
     élevée
    0.42
    Activations Density 0.002%

    No Known Activations