© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1729
    Prev
    Next
    INDEX
    Explanations

    copyright ownership

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

    The neuron is tuned to pick out tokens from license/copyright headers and version declarations (e.g. copyright, ownership, “2” in “Version 2.0,” “Util” in a module name, 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
    ueba
    -0.76
    iremos
    -0.67
     jetty
    -0.67
     molars
    -0.67
    tyw
    -0.65
    スティ
    -0.65
    <0xDB>
    -0.64
    ɔ
    -0.64
    尽
    -0.63
    ubri
    -0.63
    POSITIVE LOGITS
     Tommaso
    0.77
    Произ
    0.71
    omsday
    0.70
    nights
    0.69
     генера
    0.66
     Dann
    0.65
     reinforcement
    0.64
    skype
    0.63
    发动
    0.62
    滇
    0.61
    Activations Density 0.057%

    No Known Activations