© 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. 151053
    Prev
    Next
    INDEX
    Explanations

    marriage registers

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

    relationship and salary changes

    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
     Perce
    0.49
     Demonstr
    0.49
     perceive
    0.48
     demonstr
    0.47
     follow
    0.46
     lent
    0.46
    ی
    0.45
     large
    0.45
     therefor
    0.44
     employ
    0.43
    POSITIVE LOGITS
    XSSFSheet
    0.50
     дни
    0.47
     оружи
    0.47
    家の
    0.45
    tsprec
    0.45
    侵
    0.45
    <unused30>
    0.44
     реакции
    0.44
     BSData
    0.44
    FindingsResponse
    0.44
    Activations Density 0.000%

    No Known Activations