© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    game mods and expansions

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

    This neuron fires on technical tokens such as URLs, file-paths, version and patch numbers, and other digit-and-punctuation strings.

    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
     kathol
    -0.91
     katholischen
    -0.77
    ৮
    -0.75
    修行
    -0.71
    òn
    -0.70
    banco
    -0.70
     composites
    -0.69
     costar
    -0.69
     дево
    -0.69
     characterize
    -0.69
    POSITIVE LOGITS
     RETAIL
    1.29
     modding
    1.17
     mod
    1.13
    mods
    1.05
     Expansion
    1.05
     expansion
    1.04
    mod
    1.03
    Expansion
    1.02
    expansion
    0.99
    modification
    0.99
    Activations Density 0.094%

    No Known Activations