© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59397
    Prev
    Next
    INDEX
    Explanations

    reserved rights

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

    The neuron strongly activates on tokens common in license/copyright headers—e.g. comment‐line asterisks, “permitted,” “rights,” “reserved,” “as,” semicolons around GPL text, names/emails in copyright blocks—indicating it spots software license and copyright notice 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
     cama
    -0.73
    Tv
    -0.70
    ⚡
    -0.69
    utnik
    -0.66
    nischer
    -0.64
     dije
    -0.64
     tids
    -0.64
    onomous
    -0.64
     Tribut
    -0.64
     putih
    -0.63
    POSITIVE LOGITS
     Integrity
    0.72
    推し
    0.72
    咕
    0.68
     Bearbeitung
    0.67
     Soils
    0.67
    INPUT
    0.66
    kými
    0.66
     משפ
    0.66
     vĩnh
    0.66
    hii
    0.65
    Activations Density 0.053%

    No Known Activations