© 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. 222706
    Prev
    Next
    INDEX
    Explanations

    credit card details

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

    multilingual concepts

    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
    Tourism
    0.48
    is
    0.47
    公
    0.47
    id
    0.45
    oque
    0.45
     massif
    0.44
     hill
    0.44
    ST
    0.44
    OM
    0.44
     Tourism
    0.44
    POSITIVE LOGITS
     ബാറ്ററി
    0.49
    ของเรา
    0.47
    ร้อง
    0.47
     ჩვენ
    0.46
     دیا۔
    0.44
    ∓
    0.44
     읽
    0.43
    ສົ່ງ
    0.43
     ยาก
    0.43
     도와
    0.43
    Activations Density 0.003%

    No Known Activations