© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1354
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    mailer
    0.78
    ０
    0.77
     बवाल
    0.77
    唕
    0.77
    合法
    0.75
    ニュー
    0.73
    avasena
    0.73
    y
    0.73
     abon
    0.72
    ローマ
    0.71
    POSITIVE LOGITS
    ćen
    0.77
     ώστε
    0.70
    önt
    0.68
     contemplating
    0.66
     hands
    0.66
    িন্ন
    0.65
    ESSIONS
    0.64
     lí
    0.64
     المعادله
    0.63
     surgically
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.