© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    COPYRIGHT NOT

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

    The neuron is triggered by boilerplate license‐ and copyright‐related phrases (e.g. “DO NOT ALTER OR REMOVE COPYRIGHT NOTICES”) in code comments.

    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
    ❦
    -0.84
     és
    -0.78
    setCharacter
    -0.77
    Importante
    -0.76
    ार
    -0.76
     Delano
    -0.75
    cting
    -0.74
    だいぶ
    -0.74
     motorway
    -0.73
     افزار
    -0.73
    POSITIVE LOGITS
     stub
    1.21
    stub
    0.90
     stubs
    0.82
     visit
    0.79
     calore
    0.76
     kematian
    0.75
     outline
    0.74
    氏の
    0.74
     ultrason
    0.73
    ͫ
    0.73
    Activations Density 0.004%

    No Known Activations