© 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. 98929
    Prev
    Next
    INDEX
    Explanations

    pitch, roll, attitude, orientation

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

    The neuron fires on technical terms specifying orientation or rotational axes—especially pitch, roll, yaw, attitude, and stabilization.

    oai_token-act-pair · o4-miniTriggered 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
     был
    -1.47
     those
    -1.45
    翃
    -1.42
     because
    -1.41
     that
    -1.37
     onları
    -1.34
     them
    -1.33
     Hinblick
    -1.32
     what
    -1.30
     these
    -1.28
    POSITIVE LOGITS
     pudesse
    1.41
     verhind
    1.37
     a
    1.30
     NAME
    1.30
    lated
    1.27
    μαστε
    1.26
    𓆜
    1.23
    赑
    1.20
    *
    1.20
     kade
    1.19
    Activations Density 0.015%

    No Known Activations