© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    course, regional, multidisciplinary, language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    risto
    0.85
     crucified
    0.85
    lukan
    0.83
    .#
    0.81
    स्टेबल
    0.80
    .\\
    0.79
    .}$
    0.78
    ídia
    0.78
    ła
    0.77
    ၉
    0.77
    POSITIVE LOGITS
     Algorithms
    0.82
    Algorithms
    0.82
     Admin
    0.77
    Velocity
    0.77
    Activity
    0.76
     Architect
    0.75
    Treat
    0.75
    Admin
    0.74
     Velocity
    0.74
     Arrang
    0.73
    Activations Density 0.000%

    No Known Activations