© 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. 344
    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
    
    0.85
    🏼
    0.81
     indelible
    0.79
    ളു
    0.77
    кового
    0.77
    muslim
    0.77
     parlano
    0.77
     informée
    0.76
    completion
    0.76
     téléphonique
    0.75
    POSITIVE LOGITS
     م
    0.84
     الع
    0.80
    ان
    0.80
     krank
    0.77
     Ch
    0.76
    एम
    0.75
     Figure
    0.74
    Ch
    0.72
     도
    0.71
     निम्न
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.