© 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. 11
    Prev
    Next
    INDEX
    Explanations

    are permitted Florida

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

    This neuron detects permissive license grant language—words like “modification,” “permitted,” “provided,” and similar terms in software‐license or copyright boilerplate.

    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
     VAL
    -0.80
     insulator
    -0.77
     Val
    -0.75
    ⋄
    -0.69
     પ્ર
    -0.69
    Dto
    -0.68
     insu
    -0.66
     Dub
    -0.65
     proced
    -0.65
     OCD
    -0.65
    POSITIVE LOGITS
     иностранных
    0.78
    ած
    0.73
    DEAD
    0.70
    laki
    0.68
     tangki
    0.67
    itahu
    0.67
    entreprises
    0.66
    ⓤ
    0.66
     Elimination
    0.66
    تفسير
    0.66
    Activations Density 0.097%

    No Known Activations