© 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. 103324
    Prev
    Next
    INDEX
    Explanations

    code comments or separators

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

    The neuron activates on copyright and license header tokens (e.g. “All Rights Reserved,” “free software,” “License,” etc.) in source-code comment blocks.

    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
    好玩
    -0.82
    Ň
    -0.81
    bergen
    -0.79
     déco
    -0.77
    omethane
    -0.77
     caché
    -0.76
     enchant
    -0.75
    燻
    -0.74
    Texts
    -0.73
     zdarma
    -0.73
    POSITIVE LOGITS
    žová
    0.79
     Elektro
    0.78
     Potomac
    0.77
     Domain
    0.77
     Nr
    0.76
     arn
    0.76
    wikk
    0.75
    ONAUT
    0.75
     Colombia
    0.74
    eced
    0.74
    Activations Density 0.004%

    No Known Activations