© 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. 197669
    Prev
    Next
    INDEX
    Explanations

    required after verbs

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

    promise, smell, time, origin

    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
     пой
    0.55
     расположен
    0.50
     মেডিক্যাল
    0.48
     ಅನುಪ
    0.47
     radionu
    0.47
     расположены
    0.46
    %%%
    0.46
    ያው
    0.45
    itar
    0.45
    bew
    0.45
    POSITIVE LOGITS
    ्यूज
    0.55
    魘
    0.51
     temática
    0.50
     acabó
    0.50
     pintura
    0.48
    सायिक
    0.48
     bicicleta
    0.47
     január
    0.47
     mewah
    0.46
     pemilik
    0.46
    Activations Density 0.001%

    No Known Activations