© 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. 134894
    Prev
    Next
    INDEX
    Explanations

    business, finance, and certifications

    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
    š
    0.49
    اهرين
    0.48
    fler
    0.47
    孔
    0.46
    аль
    0.44
    feet
    0.43
    лизова
    0.43
    牥
    0.42
    凡
    0.42
    ель
    0.42
    POSITIVE LOGITS
     इट
    0.53
     الدرا
    0.52
     Bb
    0.50
    กฎ
    0.49
     occ
    0.49
     لاحظ
    0.48
     механиз
    0.48
     laws
    0.47
     WEL
    0.47
     md
    0.47
    Activations Density 0.000%

    No Known Activations