© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    Paris

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ติด
    0.65
     Giulio
    0.64
     Gabriele
    0.60
     fonction
    0.59
     Streams
    0.55
    functions
    0.53
     دلوقتي
    0.53
    殊
    0.52
    function
    0.52
    history
    0.52
    POSITIVE LOGITS
     Hilton
    0.92
     hil
    0.82
    Hil
    0.78
    ien
    0.74
    iense
    0.73
    Match
    0.72
    Texas
    0.66
    ీ
    0.66
    يان
    0.66
    奥运
    0.66
    Activations Density 0.007%

    No Known Activations