© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    software modification permissions

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

    The neuron fires on formal license header boilerplate—especially tokens like “reserved” and the surrounding punctuation (e.g. the colon) in copyright/license statements.

    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
    當地
    -0.75
    лока
    -0.72
     nhớ
    -0.72
     needn
    -0.72
    tosí
    -0.71
    guía
    -0.71
     dün
    -0.71
     käyttö
    -0.71
    ünü
    -0.70
     Dickinson
    -0.70
    POSITIVE LOGITS
     longest
    1.02
    stabili
    0.88
     companies
    0.83
    companies
    0.81
     stabilité
    0.80
    Companies
    0.78
     estabilidad
    0.77
     Gaps
    0.76
    Stab
    0.74
     espacios
    0.73
    Activations Density 0.009%

    No Known Activations