© 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. 12-GEMMASCOPE-2-RES-16K
    7. 178
    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_12_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
    ال
    0.87
    ле
    0.74
    نا
    0.74
    Giant
    0.74
     Մ
    0.73
     آم
    0.73
     giocando
    0.72
    ב
    0.71
     кни
    0.70
     showcases
    0.70
    POSITIVE LOGITS
    as
    1.05
    而是
    0.82
    ৈতিক
    0.80
    vät
    0.80
    쓴
    0.80
    뺀
    0.79
    ılması
    0.78
     μία
    0.75
    asd
    0.75
    aspect
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.