© 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. 397
    Prev
    Next
    INDEX
    Explanations

    and followed by conjunctions

    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
    ه
    1.34
    ت
    1.19
    ع
    1.19
    e
    1.15
    ي
    1.10
    क
    1.09
    ف
    1.09
    deki
    1.02
    ر
    1.02
    י
    0.98
    POSITIVE LOGITS
    を入れて
    0.81
     (
    0.78
     הם
    0.75
     slams
    0.75
    を入
    0.74
    ப்பட்ட
    0.73
    if
    0.71
     I
    0.70
    を有
    0.70
    )"
    0.69
    Activations Density 0.228%

    No Known Activations