© 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. 126
    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
    ма
    0.96
    matic
    0.87
    setzungen
    0.84
    j
    0.83
     produz
    0.78
    ammlung
    0.76
     banyaknya
    0.76
     oğlu
    0.74
    I
    0.74
    nya
    0.73
    POSITIVE LOGITS
    ेच्छा
    0.88
     DISABLE
    0.85
     cowork
    0.82
     employee
    0.80
     peruse
    0.80
    াকিস্ত
    0.79
     tirelessly
    0.78
    ס
    0.76
     admirably
    0.75
    LLY
    0.74
    Activations Density 1.561%

    No Known Activations