© 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. 114058
    Prev
    Next
    INDEX
    Explanations

    what happened

    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
    mathrm
    -2.17
     農
    -1.96
     ถ้า
    -1.95
     étan
    -1.83
     rassemb
    -1.78
    ᚔ
    -1.76
    where
    -1.73
    臜
    -1.73
    妡
    -1.73
    蹰
    -1.70
    POSITIVE LOGITS
     those
    2.16
     Obviously
    2.13
     in
    1.92
     Essentially
    1.86
     this
    1.85
     Undoubtedly
    1.84
     Certainly
    1.83
     Throughout
    1.78
     about
    1.74
     Basically
    1.70
    Activations Density 0.012%

    No Known Activations