© 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. 219365
    Prev
    Next
    INDEX
    Explanations

    financial services and income

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

    assessment of features

    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
    거
    0.48
    意义
    0.48
    百分
    0.48
    могою
    0.48
    у
    0.48
    숫
    0.48
    экс
    0.46
    ‰
    0.46
    无法
    0.46
    не
    0.45
    POSITIVE LOGITS
     deploying
    0.50
     sounded
    0.50
     Ascension
    0.49
     ;;
    0.48
     alam
    0.48
     applicable
    0.48
     Han
    0.48
     Hak
    0.47
     Hassan
    0.46
     Bae
    0.46
    Activations Density 0.001%

    No Known Activations