© 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. 117066
    Prev
    Next
    INDEX
    Explanations

    legal cases and copyright notices

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

    The neuron detects legal‐boilerplate and metadata tokens (e.g. “Copyright,” “License,” “Plaintiff,” “Defendant,” “Affiliates,” and associated numbers) typically found in document headers.

    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
    ְר
    -0.88
    考生
    -0.88
    asley
    -0.85
    линг
    -0.84
    Franklin
    -0.82
    惬
    -0.80
     JsonResponse
    -0.79
    klas
    -0.77
    atste
    -0.77
    publik
    -0.75
    POSITIVE LOGITS
    uggles
    0.79
     поса
    0.79
    Planting
    0.69
     lẽ
    0.68
    aval
    0.66
    自身が
    0.65
     samba
    0.65
     worldview
    0.64
     COT
    0.63
     janitor
    0.63
    Activations Density 0.046%

    No Known Activations