© 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. 168938
    Prev
    Next
    INDEX
    Explanations

    poverty rate, household income, precinct

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

    census bureau demographic data

    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
    दुनिया
    0.41
    extend
    0.40
    蛆
    0.39
     sevent
    0.38
    멤버
    0.37
    ⒎
    0.36
    全世界
    0.36
    BRAS
    0.35
    মহাদেশ
    0.35
     হান
    0.35
    POSITIVE LOGITS
     commuting
    0.49
     ρ
    0.48
     precinct
    0.45
     Barrio
    0.45
     barrio
    0.44
     Precinct
    0.44
     Households
    0.43
     Carpenter
    0.43
     എടു
    0.42
     households
    0.42
    Activations Density 0.067%

    No Known Activations