© 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. 16181
    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
    ９
    0.89
    ৫৮
    0.83
    extensions
    0.81
    nxt
    0.79
    novae
    0.79
    ۴
    0.79
    nodo
    0.78
    
    0.76
     ۹
    0.75
    ۵
    0.75
    POSITIVE LOGITS
     condiment
    0.76
     使っ
    0.74
     havoc
    0.72
     condiments
    0.72
     exagger
    0.71
     fenders
    0.71
     geniuses
    0.70
     smears
    0.70
     rebuttal
    0.70
     boobs
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.