© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    En, Ben, or words starting with 'en', 'ben'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     Urbana
    0.92
     mulberry
    0.91
    arks
    0.85
     inscrito
    0.82
    ilir
    0.82
    cca
    0.81
    ivere
    0.81
    嶼
    0.81
     listas
    0.81
    oría
    0.80
    POSITIVE LOGITS
     Ben
    2.02
    Ben
    1.98
     BEN
    1.91
     EN
    1.81
     En
    1.76
    En
    1.70
    EN
    1.68
     Bén
    1.62
    Ten
    1.60
     Ten
    1.60
    Activations Density 0.263%

    No Known Activations