© 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. 38453
    Prev
    Next
    INDEX
    Explanations

    microsoft Edge

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

    The neuron is keyed to boilerplate copyright and licensing text (e.g. “Microsoft” in URLs, “Copyright,” “License,” “You should have received a copy…”).

    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
    Fus
    -0.69
     PROFILE
    -0.68
     Whitley
    -0.67
     Samb
    -0.66
    ू
    -0.65
     решения
    -0.65
    Джерела
    -0.64
    rod
    -0.64
    Mirage
    -0.64
    ilet
    -0.63
    POSITIVE LOGITS
     око
    0.67
     insufic
    0.66
    લા
    0.66
     Kleider
    0.65
    Cov
    0.65
     partid
    0.64
     meyd
    0.63
    CEE
    0.63
    iba
    0.62
    proteins
    0.62
    Activations Density 0.097%

    No Known Activations