© 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. 124975
    Prev
    Next
    INDEX
    Explanations

    parts and infrastructure

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

    product names and origins

    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
     जश्न
    0.55
     poesia
    0.52
     poesía
    0.51
     شادی
    0.50
    酺
    0.50
    预约
    0.49
     videolar
    0.49
     două
    0.48
     கதாபாத்திர
    0.48
    籁
    0.47
    POSITIVE LOGITS
     product
    0.52
    product
    0.52
     Xinhua
    0.51
     Jiangsu
    0.48
    w
    0.48
    operate
    0.48
     China
    0.47
     analyte
    0.47
     efficient
    0.46
     metallurgical
    0.46
    Activations Density 0.001%

    No Known Activations