© 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. 231392
    Prev
    Next
    INDEX
    Explanations

    business sectors and finance

    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
     одного
    0.46
     Shu
    0.46
     Angebot
    0.46
     ش
    0.45
     شو
    0.45
     তা
    0.44
     צי
    0.44
     ring
    0.44
     ת
    0.44
     shingles
    0.44
    POSITIVE LOGITS
    味料
    0.48
    떻
    0.46
    腦
    0.46
    ьте
    0.45
    다른
    0.44
    همه
    0.44
    冀
    0.44
    дино
    0.44
    まま
    0.42
    뇌
    0.42
    Activations Density 0.001%

    No Known Activations