© 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. 67374
    Prev
    Next
    INDEX
    Explanations

    generation corn

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

    code components and technical terms

    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
    ığında
    0.46
     ICRC
    0.44
     осталось
    0.43
     није
    0.43
    ્યા
    0.43
     inducted
    0.43
    
    0.43
     गुस्से
    0.42
    j
    0.42
     indignant
    0.42
    POSITIVE LOGITS
    景点
    0.50
     Oahu
    0.46
    رس
    0.44
    အစိတ်အပိုင်း
    0.44
    周边
    0.43
    相应
    0.43
    스를
    0.43
     würden
    0.42
    校园
    0.42
     walkable
    0.41
    Activations Density 0.001%

    No Known Activations