© 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. 2510
    Prev
    Next
    INDEX
    Explanations

    place names and dates

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

    This neuron fires on MediaWiki article‐formatting markup (e.g. the “__NO TOC__” token, standalone underscores, section‐heading numbers, and similar markup tokens).

    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
     profils
    -0.82
    膜
    -0.79
     advertisers
    -0.73
     zmien
    -0.70
    Parser
    -0.70
     methodologies
    -0.70
    parseDouble
    -0.69
     Luke
    -0.69
     Erinnerung
    -0.69
    LayoutInflater
    -0.68
    POSITIVE LOGITS
    FEMALE
    0.73
    landschaft
    0.65
    冱
    0.64
     męska
    0.63
    ILLUSTRATION
    0.63
    quisa
    0.63
     Fore
    0.63
     Clor
    0.62
    ostasis
    0.62
    ariat
    0.62
    Activations Density 0.096%

    No Known Activations