© 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. 167
    Prev
    Next
    INDEX
    Explanations

    documentation or general language

    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
    wirkungen
    0.73
    став
    0.71
    ше
    0.70
     ໜ
    0.70
    ски
    0.69
    ベスト
    0.69
    adale
    0.68
     τό
    0.68
    ства
    0.66
    atial
    0.66
    POSITIVE LOGITS
     asphalt
    0.85
     équipé
    0.84
     restent
    0.83
    ിയത്
    0.82
    0
    0.80
     kilow
    0.80
     microphones
    0.79
     incroyable
    0.79
    <?
    0.78
    પૂર્ણ
    0.76
    Activations Density 0.000%

    No Known Activations