© 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. 101
    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
    an
    0.88
    at
    0.82
    ğini
    0.79
    ل
    0.79
    zelfde
    0.77
    n
    0.73
    ن
    0.70
    nione
    0.69
    al
    0.68
    or
    0.67
    POSITIVE LOGITS
    '
    0.77
    인
    0.67
    \
    0.65
    $
    0.65
     than
    0.61
     will
    0.60
     be
    0.59
     takes
    0.59
     calipers
    0.58
    வ
    0.58
    Activations Density 0.534%

    No Known Activations