© 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. 174295
    Prev
    Next
    INDEX
    Explanations

    world economy

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

    income, students, teachers, viewership

    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
     scambio
    0.53
     appropriation
    0.47
     strument
    0.43
     pdf
    0.42
     hugely
    0.42
     for
    0.42
    पूर्वी
    0.42
    릴
    0.42
     jpeg
    0.42
    人々
    0.41
    POSITIVE LOGITS
    ifiers
    0.55
    erdere
    0.53
    iers
    0.52
     दिया
    0.51
    azem
    0.50
    ierd
    0.50
    az
    0.48
    izers
    0.47
    oua
    0.47
    벧
    0.47
    Activations Density 0.000%

    No Known Activations