© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    protection agency

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

    government agencies, particularly the Environmental Protection Agency (EPA), in legal and regulatory contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    -1.15
    stehen
    -1.08
     at
    -1.05
     IMPORTANT
    -1.05
     erosion
    -1.03
     Maybe
    -1.03
    vé
    -1.02
     melaporkan
    -1.02
    endalikan
    -1.02
     as
    -1.01
    POSITIVE LOGITS
     {$\
    1.29
    🧌
    1.27
     metais
    1.27
     comanda
    1.24
    撣
    1.21
     広場
    1.20
     maestra
    1.16
     trast
    1.15
     Fichier
    1.14
    orgio
    1.14
    Activations Density 0.104%

    No Known Activations