© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144316
    Prev
    Next
    INDEX
    Explanations

    laws, regulations, or service terms

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

    family connection or server connection

    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
    Negative Logits
     soiled
    0.49
    ittance
    0.49
    κού
    0.46
     elector
    0.46
     unpacking
    0.45
     horrified
    0.45
     주문
    0.45
     crippled
    0.45
    мед
    0.44
    옐
    0.44
    POSITIVE LOGITS
    ON
    0.45
    OT
    0.45
     weitere
    0.45
    OC
    0.44
    dagen
    0.44
     Develop
    0.43
     Schedule
    0.43
    渶
    0.43
    ONO
    0.43
     Attachment
    0.42
    Activations Density 0.003%

    No Known Activations