© 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. 56861
    Prev
    Next
    INDEX
    Explanations

    cruise control and collision avoidance

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

    This neuron activates on technical or domain-specific terminology—project or product names, acronyms, and numeric specifications.

    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
    UObject
    -0.73
     Blom
    -0.73
     GeForce
    -0.73
     Lira
    -0.71
     PvE
    -0.69
    hbase
    -0.69
    ☐
    -0.68
    팡
    -0.68
    filé
    -0.68
    键盘
    -0.68
    POSITIVE LOGITS
     cruise
    1.84
     Cruise
    1.37
    Cruise
    1.34
     adaptive
    1.30
    cruise
    1.24
     Adaptive
    1.15
     Control
    1.09
     control
    1.05
    adaptive
    0.98
    Adaptive
    0.97
    Activations Density 0.015%

    No Known Activations