© 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. 34604
    Prev
    Next
    INDEX
    Explanations

    any later version

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

    The neuron fires on bits of free‐software license boilerplate—specifically on the “you can redistribute and/or modify … under the terms of the GNU … version … or any later version” phrasing.

    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
     útiles
    -0.75
     તે
    -0.73
     Foss
    -0.72
    naked
    -0.70
    utados
    -0.68
    смотрен
    -0.67
    въ
    -0.66
    acamata
    -0.66
    слет
    -0.66
    kir
    -0.65
    POSITIVE LOGITS
    etcode
    0.69
     dined
    0.68
    tgärder
    0.66
    zünd
    0.65
    
    0.65
    onar
    0.64
    的需求
    0.64
    帧
    0.64
     Zerst
    0.63
    Driven
    0.63
    Activations Density 0.047%

    No Known Activations