© 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. 224428
    Prev
    Next
    INDEX
    Explanations

    sale proceeds

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

    descriptive phrases follow common words

    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
    箬
    0.54
     emit
    0.51
     funkcji
    0.50
    
    0.50
     ресурсов
    0.49
     વોર્
    0.48
    或者
    0.48
    ніх
    0.46
    或
    0.46
    Vaterpolo
    0.46
    POSITIVE LOGITS
    ut
    0.61
    ie
    0.55
    atta
    0.55
    us
    0.52
    ad
    0.50
    watching
    0.50
     hanging
    0.50
    ana
    0.49
    atang
    0.49
    yta
    0.48
    Activations Density 0.001%

    No Known Activations