© 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. 34-GEMMASCOPE-RES-131K
    7. 79365
    Prev
    Next
    INDEX
    Explanations

    web programming utilities

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     during
    -0.98
     still
    -0.95
     for
    -0.92
     incredible
    -0.91
     seemingly
    -0.91
     really
    -0.88
     came
    -0.88
     Kondisi
    -0.88
     constantly
    -0.88
     even
    -0.85
    POSITIVE LOGITS
    龇
    1.10
     creadores
    1.06
    herit
    1.03
     HUMAN
    1.02
    ilist
    1.02
    ≥
    0.99
    perhaps
    0.99
    roughly
    0.98
    nare
    0.97
    Iq
    0.92
    Activations Density 0.001%

    No Known Activations