© 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. 78862
    Prev
    Next
    INDEX
    Explanations

    free software and redistribute

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

    This neuron activates on boilerplate from open-source software licenses, especially permission words like “redistribute” and “modify.”

    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
     will
    -0.75
     สาม
    -0.74
     especially
    -0.72
    chová
    -0.72
     erwähnt
    -0.71
    ();
    -0.71
     صوتيه
    -0.71
     demonstrate
    -0.70
     کرت
    -0.70
    QtGui
    -0.69
    POSITIVE LOGITS
    ได้
    4.78
     được
    3.91
     get
    2.97
     gets
    2.33
    得到
    2.22
    得了
    2.13
     getting
    2.02
    get
    1.93
     got
    1.92
     få
    1.88
    Activations Density 0.004%

    No Known Activations