Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 298
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ک
    0.43
    т
    0.39
    त
    0.38
     extraordinaire
    0.37
    ت
    0.37
     nicht
    0.36
     œufs
    0.36
    im
    0.36
     actuelle
    0.36
     exquisite
    0.36
    POSITIVE LOGITS
    2
    0.34
    几十
    0.31
    檯
    0.29
    ामुळे
    0.28
    file
    0.28
    ucky
    0.27
    лна
    0.27
    ract
    0.27
    room
    0.27
    就不
    0.26
    Activations Density 15.845%

    No Known Activations