© 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. 95690
    Prev
    Next
    INDEX
    Explanations

    civilian and military roles

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

    groups and commerce

    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
    优秀
    0.47
    伟大
    0.47
    i
    0.46
    碗
    0.45
    坟
    0.44
    〃
    0.44
    北美
    0.44
    e
    0.43
    规
    0.43
    碱
    0.43
    POSITIVE LOGITS
     households
    0.64
     craftsmen
    0.57
     dwellers
    0.55
     residents
    0.55
     adventurers
    0.54
     shoppers
    0.53
     housewives
    0.53
     villagers
    0.52
     apartments
    0.51
     cottages
    0.51
    Activations Density 0.001%

    No Known Activations