© 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. 114208
    Prev
    Next
    INDEX
    Explanations

    mature

    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
    ৢ
    -3.38
     REALLY
    -2.75
     crucial
    -2.70
    쨩
    -2.63
    盉
    -2.56
    ሏ
    -2.53
     asesor
    -2.50
     hefty
    -2.48
    鲞
    -2.48
     связанные
    -2.47
    POSITIVE LOGITS
     dazzling
    3.06
     allow
    3.06
    i
    2.77
    Even
    2.72
     unrelenting
    2.67
     While
    2.64
    ly
    2.64
    While
    2.59
     dizzy
    2.59
    In
    2.55
    Activations Density 0.004%

    No Known Activations