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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47903
    Prev
    Next
    INDEX
    Explanations

    Report abuse, bugs, issue

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

    The neuron strongly activates on the boilerplate “Permission…shall be included…” style language found in open‐source software licenses.

    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
    渴
    -0.75
    acknowledge
    -0.72
     Booker
    -0.71
    heureusement
    -0.67
    bsc
    -0.66
     epile
    -0.66
    парта
    -0.65
     galleries
    -0.65
     Frat
    -0.64
    堀
    -0.63
    POSITIVE LOGITS
    瞓
    0.71
    <0xAE>
    0.70
     מח
    0.66
    Dod
    0.66
     аку
    0.65
    וה
    0.64
     mencu
    0.64
    closure
    0.63
    dod
    0.63
    果汁
    0.63
    Activations Density 0.077%

    No Known Activations