© 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. 231623
    Prev
    Next
    INDEX
    Explanations

    normally followed by engage

    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
     pusieron
    0.55
     жена
    0.52
     mensuales
    0.49
     женой
    0.49
     différen
    0.48
    origines
    0.47
     volvió
    0.47
    {//
    0.46
    aunque
    0.46
     puisqu
    0.46
    POSITIVE LOGITS
     Home
    0.49
    ನ್
    0.47
     Include
    0.46
    న్
    0.44
     blend
    0.44
     Than
    0.43
    ান
    0.43
    न्दे
    0.42
    보다
    0.42
    ੈ
    0.42
    Activations Density 0.000%

    No Known Activations