© 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. 243775
    Prev
    Next
    INDEX
    Explanations

    financial report, encourage parents

    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
     เมตร
    0.61
     政府
    0.54
     则
    0.50
     总
    0.50
     设计
    0.50
    𢎞
    0.50
    낵
    0.49
     CtApp
    0.48
    ት
    0.48
     রাইফ
    0.48
    POSITIVE LOGITS
    sthrough
    0.47
     subserv
    0.47
     lith
    0.45
    grado
    0.44
    lect
    0.44
    ology
    0.43
     بیٹھ
    0.42
    st
    0.42
     ist
    0.42
    bon
    0.42
    Activations Density 0.000%

    No Known Activations