© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83328
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron strongly activates on occurrences of formal software‐license terms (e.g. “Licensed,” “License,” etc.).

    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
    ulier
    -0.82
     Corridor
    -0.78
    坂
    -0.77
    IBAction
    -0.73
    XB
    -0.71
     Hawke
    -0.71
    tony
    -0.71
     THOR
    -0.70
     Thor
    -0.69
    banden
    -0.69
    POSITIVE LOGITS
     ноября
    0.67
    ๘
    0.66
    税込
    0.63
     Langen
    0.63
     lần
    0.63
    使其
    0.63
     proie
    0.63
     divina
    0.62
     romana
    0.62
     buffet
    0.61
    Activations Density 0.072%

    No Known Activations