© 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. 164787
    Prev
    Next
    INDEX
    Explanations

    employment and finance concepts

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

    seen this before

    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
    도는
    0.48
    ículos
    0.48
    ადი
    0.48
    жет
    0.47
    도를
    0.46
    是因为
    0.45
     메서
    0.45
    菠
    0.45
    芒果
    0.44
    钻石
    0.44
    POSITIVE LOGITS
     earning
    0.51
     pensioners
    0.49
     droits
    0.49
     earners
    0.47
     replacement
    0.45
     abolition
    0.44
     employer
    0.44
     refineries
    0.44
     Bf
    0.43
     bittern
    0.43
    Activations Density 0.000%

    No Known Activations