© 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. 125418
    Prev
    Next
    INDEX
    Explanations

    KRF

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

    country variations and price elasticity

    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
    -
    0.66
    :
    0.56
    ,
    0.54
    ;
    0.51
    an
    0.50
    in
    0.48
    形容
    0.48
    (
    0.48
    ↵↵
    0.47
    请
    0.46
    POSITIVE LOGITS
    ড়যন্ত্র
    0.49
    ন্ত্রণাল
    0.47
     bourse
    0.47
    وسیع
    0.43
    𝒹
    0.43
     rebellion
    0.43
    द्य
    0.43
    뽐
    0.43
    actionBarTab
    0.42
     futures
    0.42
    Activations Density 0.002%

    No Known Activations