© 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. 31060
    Prev
    Next
    INDEX
    Explanations

    copyright statements

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

    This neuron detects boilerplate copyright/license header phrases, especially the “the original author or authors” segment.

    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
    debe
    -0.87
    お手
    -0.82
    autoIncrement
    -0.80
     навіть
    -0.78
     причем
    -0.77
     அவ
    -0.77
    リカ
    -0.75
    以上です
    -0.74
    viated
    -0.74
     bliver
    -0.74
    POSITIVE LOGITS
    putra
    0.98
     seleccione
    0.94
     GIPHY
    0.93
    度的
    0.87
     király
    0.85
    年も
    0.85
    vägen
    0.85
    的に
    0.84
     yağı
    0.83
    tsky
    0.82
    Activations Density 0.393%

    No Known Activations