© 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. 136513
    Prev
    Next
    INDEX
    Explanations

    foreign cities and names

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

    multiple strikes

    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
    步行
    0.49
    nelle
    0.46
    地下
    0.45
    颖
    0.44
     Technology
    0.43
    错
    0.43
    ğı
    0.43
    享
    0.43
    钛
    0.42
    汽车
    0.41
    POSITIVE LOGITS
     после
    0.57
     gangsters
    0.57
     rubles
    0.56
     robberies
    0.55
     ocasiones
    0.54
     posle
    0.51
     евре
    0.49
     gevallen
    0.49
     gallons
    0.49
    কমার
    0.49
    Activations Density 0.000%

    No Known Activations