© 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. 79233
    Prev
    Next
    INDEX
    Explanations

    software licenses and terms

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

    The neuron is firing on open‐license boilerplate—especially tokens from license names and URLs (e.g. Creative Commons or Apache license headers).

    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
     these
    -0.86
     do
    -0.85
     many
    -0.85
     with
    -0.85
     going
    -0.84
     implying
    -0.83
     both
    -0.83
     if
    -0.82
     operational
    -0.82
    +{
    -0.81
    POSITIVE LOGITS
    creativecommons
    1.04
    Creative
    1.00
    Oby
    0.99
    서울
    0.91
     révolution
    0.90
     Attribution
    0.89
     chmod
    0.89
    Monument
    0.88
     LUT
    0.88
    Unlimited
    0.88
    Activations Density 0.022%

    No Known Activations