© 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. 30170
    Prev
    Next
    INDEX
    Explanations

    intervene or intervention

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

    The neuron detects mentions of “intervene” (and its morphological variants such as intervened, intervention, intervening).

    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
     alternatively
    -1.04
    WAKE
    -0.94
     concurrently
    -0.89
    읊
    -0.89
     principaux
    -0.88
     Ammonium
    -0.88
    품
    -0.87
    神
    -0.86
     sièges
    -0.85
    ického
    -0.85
    POSITIVE LOGITS
     in
    1.49
     into
    1.37
     intervention
    1.35
     Intervention
    1.19
     intervene
    1.13
     with
    1.09
    Intervention
    1.09
     interventions
    1.02
     interfere
    1.02
     to
    1.01
    Activations Density 0.016%

    No Known Activations