© 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. 248329
    Prev
    Next
    INDEX
    Explanations

    graphic sweatshirts

    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
    u
    0.50
     hybr
    0.49
    rédients
    0.48
    Hybrid
    0.48
     Hybrid
    0.47
    q
    0.47
    r
    0.46
    hybrid
    0.46
    filter
    0.46
    medium
    0.44
    POSITIVE LOGITS
     serviços
    0.52
     му
    0.50
    ў
    0.48
     सेवा
    0.48
     女
    0.47
     меню
    0.46
    ॉक
    0.46
     usługi
    0.46
     शे
    0.44
     Nant
    0.44
    Activations Density 0.000%

    No Known Activations