© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85532
    Prev
    Next
    INDEX
    Explanations

    games and technical terms

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

    The neuron fires on capitalized, game‐related proper nouns—especially video game titles, level names, and in-game item or weapon names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    including
    -1.34
    \'
    -1.33
     in
    -1.27
     with
    -1.27
    on
    -1.26
    {
    -1.25
     Jugendlichen
    -1.19
     a
    -1.16
    رفه
    -1.16
    at
    -1.15
    POSITIVE LOGITS
    новение
    1.38
    Intérieur
    1.28
    MIDDLEWARE
    1.28
    maic
    1.20
    eficiente
    1.16
     gustado
    1.16
     Madd
    1.16
    eBook
    1.14
    erape
    1.13
    nagem
    1.13
    Activations Density 0.008%

    No Known Activations