© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    power supply, PSU shroud

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags technical hardware specification details—especially model numbers, capacities, and power‐related numeric specs.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     shaded
    -0.73
     ErrIntOverflow
    -0.73
     Malayalam
    -0.71
     доступ
    -0.69
     porta
    -0.69
     використовувати
    -0.66
     charisma
    -0.66
    快速
    -0.66
     festge
    -0.66
     Cameroon
    -0.66
    POSITIVE LOGITS
     modular
    1.09
     Bronze
    1.02
    modular
    1.00
    Bronze
    0.95
     Modular
    0.94
    Modular
    0.94
     EFFICIENCY
    0.92
     bronze
    0.87
     Efficiency
    0.86
    buntu
    0.84
    Activations Density 0.021%

    No Known Activations