© 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. 15656
    Prev
    Next
    INDEX
    Explanations

    internal combustion engines

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

    This neuron detects technical references to internal‐combustion engines and their fuel systems.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sólidos
    -1.20
    coloured
    -1.16
    艽
    -1.16
     hidráulica
    -1.14
     uren
    -1.12
     münchen
    -1.11
     Jahrhunderts
    -1.10
     RECIPES
    -1.07
     vea
    -1.07
     ellen
    -1.07
    POSITIVE LOGITS
     betreffenden
    1.09
    ६
    1.06
     determine
    1.04
     '+':
    1.02
     MDS
    1.00
     thăm
    0.98
     erwähnten
    0.98
     смесь
    0.98
     menschlichen
    0.97
     pronti
    0.96
    Activations Density 0.071%

    No Known Activations