© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92913
    Prev
    Next
    INDEX
    Explanations

    integrating sensing, monitoring, detecting

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

    The neuron primarily activates on technical terms related to radiation measurement and dosimetry (e.g., “radon,” “concentration,” “dosimeters,” “radiation”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     spodnie
    -0.86
     Partager
    -0.81
     thoải
    -0.80
    utoff
    -0.76
    urnal
    -0.75
     bocca
    -0.74
     résoudre
    -0.74
     Dare
    -0.74
    hibit
    -0.74
    Forrás
    -0.73
    POSITIVE LOGITS
     integrating
    1.46
     dosi
    1.30
     Integrating
    1.30
    integrating
    1.27
    Integrating
    1.27
     integrate
    1.25
     integrates
    1.24
     Integr
    1.14
     integration
    1.12
     integrative
    1.12
    Activations Density 0.062%

    No Known Activations