© 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. 252
    Prev
    Next
    INDEX
    Explanations

    transactional email

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    afe
    0.86
    適
    0.81
    но
    0.80
    에서도
    0.80
    総
    0.77
    リズム
    0.77
     друго
    0.77
    取り付け
    0.76
    psie
    0.76
    aglia
    0.75
    POSITIVE LOGITS
     endow
    0.92
     headsets
    0.85
     gminy
    0.82
    ಥವಾ
    0.80
    groomed
    0.80
    сных
    0.79
     Glast
    0.78
    うる
    0.77
    ья
    0.77
    篤
    0.77
    Activations Density 0.000%

    No Known Activations