© 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. 62621
    Prev
    Next
    INDEX
    Explanations

    valve, antenna, electrode, coil, anode

    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
     introvert
    -0.94
     femininos
    -0.92
    production
    -0.85
    Mario
    -0.85
    erschein
    -0.85
    Titulo
    -0.84
     przyjem
    -0.83
     merveille
    -0.83
     japonaise
    -0.83
    ulating
    -0.82
    POSITIVE LOGITS
     selection
    1.55
     choice
    1.45
     placement
    1.43
     configuration
    1.31
     size
    1.30
     sizes
    1.23
     manufacturers
    1.22
     position
    1.20
     manufacturer
    1.19
     usage
    1.16
    Activations Density 0.166%

    No Known Activations