© 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. 93514
    Prev
    Next
    INDEX
    Explanations

    copyright and license terms

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

    The neuron strongly activates on comment‐block and license header tokens—especially the closing comment delimiter “*/” and other boilerplate copyright/license keywords—so it’s detecting license/copyright comment sections.

    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
     ramai
    -1.02
     خوردن
    -0.93
    styr
    -0.89
     toit
    -0.85
     hermano
    -0.84
    hashtags
    -0.84
    ktur
    -0.81
     controles
    -0.81
    鼉
    -0.81
     Temporada
    -0.80
    POSITIVE LOGITS
    oredCriteria
    0.88
     acorns
    0.88
     сочи
    0.85
     criteria
    0.81
     super
    0.77
     order
    0.76
     synthe
    0.75
    hav
    0.73
     Forder
    0.71
    éu
    0.71
    Activations Density 0.000%

    No Known Activations