© 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. 58190
    Prev
    Next
    INDEX
    Explanations

    unemployment claims and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Tieren
    -1.26
     عاما
    -1.22
    Each
    -1.18
    '],
    -1.17
     chuť
    -1.15
    すぎた
    -1.14
     Relating
    -1.13
    ІІ
    -1.13
     Examining
    -1.10
    [:,:,
    -1.09
    POSITIVE LOGITS
     Unemployment
    1.42
     Benefits
    1.23
     Skills
    1.23
     Types
    1.11
    <i>
    1.10
     Return
    1.10
     then
    1.08
     Unity
    1.07
    ian
    1.07
     unemployment
    1.06
    Activations Density 0.046%

    No Known Activations