© 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. 97038
    Prev
    Next
    INDEX
    Explanations

    intensifier-descriptive word pairings

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

    AI-powered solutions for teams

    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
     вечер
    0.45
    িপ্ত
    0.44
    unkte
    0.42
     stek
    0.42
    ：
    0.42
    Databaze
    0.41
    Ǧ
    0.41
    Db
    0.40
     exposureButton
    0.40
     konkur
    0.39
    POSITIVE LOGITS
     you
    0.48
     सीरियल
    0.48
    مي
    0.45
     nhớ
    0.45
    गिंग
    0.45
     phút
    0.44
    train
    0.43
    洙
    0.43
    uum
    0.43
     direct
    0.43
    Activations Density 0.001%

    No Known Activations