© 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. 118786
    Prev
    Next
    INDEX
    Explanations

    software licensing or court opinions

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

    The neuron is highly selective for the exact token “Software,” especially in formal license or header contexts.

    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
     affects
    -0.80
    ควร
    -0.74
     burbu
    -0.73
     pliable
    -0.73
     seems
    -0.73
     McCarty
    -0.73
     rares
    -0.72
    domés
    -0.72
     plagioclase
    -0.72
    कृ
    -0.71
    POSITIVE LOGITS
    ంక
    0.90
    Spear
    0.86
     Spear
    0.85
    җ
    0.85
    ferent
    0.84
     HttpHeaders
    0.84
     lắm
    0.83
     petal
    0.82
    CLC
    0.81
     viviendo
    0.81
    Activations Density 0.002%

    No Known Activations