© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149703
    Prev
    Next
    INDEX
    Explanations

    deals daily

    np_acts-logits-general · gemini-2.5-flash-lite

    practical clothing and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ंसिल
    0.51
    म
    0.50
    सवाल
    0.50
     Annot
    0.49
    missing
    0.49
    BLACK
    0.48
    उथ
    0.48
    Bert
    0.48
     Communicate
    0.47
     ट्रेड
    0.46
    POSITIVE LOGITS
    罔
    0.46
     entrambi
    0.46
    дела
    0.45
     vinaig
    0.45
    QueueMutex
    0.45
     fring
    0.45
    netHex
    0.44
    їв
    0.43
     HTTPS
    0.43
    ouve
    0.42
    Activations Density 0.000%

    No Known Activations