© 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. 227909
    Prev
    Next
    INDEX
    Explanations

    administrative and medical 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
    て
    0.52
     Assemblies
    0.50
     Constraints
    0.48
     Parl
    0.48
     Estim
    0.47
     Files
    0.47
    ན་
    0.46
    会儿
    0.46
    劳动
    0.46
    军队
    0.45
    POSITIVE LOGITS
    bereitung
    0.52
    zuk
    0.52
     ผม
    0.50
     Люди
    0.50
    ഞ
    0.49
    zan
    0.47
    zap
    0.47
    folk
    0.45
     ياس
    0.45
     कुठे
    0.45
    Activations Density 0.000%

    No Known Activations