© 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. 8566
    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
    。
    0.78
    公元
    0.75
    ।
    0.73
    尔多
    0.72
    j
    0.69
    ında
    0.69
    ۔
    0.69
    ী
    0.68
    ان
    0.68
    3
    0.67
    POSITIVE LOGITS
     doesn
    1.00
     viewership
    0.87
     salespeople
    0.86
     salesperson
    0.85
     volonté
    0.82
     tricked
    0.82
     jogo
    0.81
     unwillingness
    0.81
     uniquement
    0.79
     não
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.