© 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. 136932
    Prev
    Next
    INDEX
    Explanations

    advisors, ton, city, trouble, reduce, versus

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

    context window size

    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
    rends
    0.47
    collectibles
    0.44
    पेड
    0.43
    ych
    0.42
    irth
    0.42
    hift
    0.42
    )}=\
    0.41
    rato
    0.41
    rentes
    0.41
     misery
    0.41
    POSITIVE LOGITS
    ம்பு
    0.44
     участке
    0.44
     воздуха
    0.44
     потен
    0.43
     nguyện
    0.43
     πραγμα
    0.42
     AutoML
    0.42
    вості
    0.41
    зна
    0.41
    篩
    0.41
    Activations Density 0.000%

    No Known Activations