© 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. 525
    Prev
    Next
    INDEX
    Explanations

    Natural Language Processing

    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
     impost
    1.06
     “
    0.86
    opacity
    0.86
     pro
    0.86
    od
    0.84
     "
    0.84
     ar
    0.84
    ுகள்
    0.82
     pad
    0.81
     af
    0.80
    POSITIVE LOGITS
    في
    1.09
    ロウ
    1.02
    ю
    1.02
    トレーニング
    1.00
    बारक
    1.00
    ي
    0.99
    出
    0.99
    ३
    0.99
    コア
    0.98
    טו
    0.98
    Activations Density 0.001%

    No Known Activations