© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15553
    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
     Video
    0.91
    nhs
    0.87
     ########.
    0.85
     Αν
    0.84
     الفيديو
    0.81
    OHA
    0.79
     그래서
    0.79
     Remarkably
    0.79
     비
    0.77
     文
    0.77
    POSITIVE LOGITS
    ीकृत
    0.80
     receptacle
    0.78
    avasena
    0.73
    ślin
    0.73
    esti
    0.73
    gown
    0.72
    otype
    0.71
     summar
    0.71
     ausschließlich
    0.71
    ilangkan
    0.71
    Activations Density 0.002%

    No Known Activations