© 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. 113609
    Prev
    Next
    INDEX
    Explanations

    collective bargaining

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

    sectionIP addressessquare footagetragic events

    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
     వ
    0.52
    覬
    0.52
     theology
    0.50
    ებ
    0.48
     सोम
    0.47
     PhoneNumber
    0.47
     衣
    0.47
     hypothesized
    0.46
     書
    0.46
    gård
    0.46
    POSITIVE LOGITS
     Novem
    0.47
    o
    0.46
     lequel
    0.46
     বর্ধ
    0.46
    ہوری
    0.46
     allong
    0.46
     Espírito
    0.45
     Signore
    0.44
    汇报
    0.44
    airement
    0.44
    Activations Density 0.000%

    No Known Activations