© 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. 79390
    Prev
    Next
    INDEX
    Explanations

    software permission or configuration

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

    The neuron fires strongly on the word “granted,” i.e. it detects the grant‐of‐permission phrasing you see in software licenses.

    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
     esbo
    -0.85
    __(/*!
    -0.82
    defn
    -0.81
     coffee
    -0.81
     köt
    -0.80
     ventilador
    -0.77
     farol
    -0.76
     Madhya
    -0.75
     mû
    -0.75
    驅
    -0.74
    POSITIVE LOGITS
    INA
    0.91
     tartar
    0.90
     petri
    0.79
    accine
    0.79
    énario
    0.79
    rées
    0.77
     docu
    0.74
     Да
    0.73
    UTO
    0.73
    AMPLE
    0.73
    Activations Density 0.000%

    No Known Activations