© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11294
    Prev
    Next
    INDEX
    Explanations

    WSL2, sonnet, autobahn

    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_24_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
    و
    0.84
     Leisure
    0.83
    zca
    0.82
     libres
    0.78
    er
    0.75
    ﹔
    0.73
     vlastní
    0.73
    ゝ
    0.73
     भंडार
    0.73
    brochen
    0.73
    POSITIVE LOGITS
     renseignements
    0.87
    この
    0.82
     intitul
    0.79
     congregate
    0.77
     disposition
    0.75
    東京
    0.75
     predisposition
    0.74
     monograph
    0.74
     importantly
    0.72
    ❤️❤️
    0.72
    Activations Density 0.001%

    No Known Activations