© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20755
    Prev
    Next
    INDEX
    Explanations

    PlayStation consoles and versions

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

    The neuron strongly activates on mentions of PlayStation (and related “PS”) console names and their model numbers.

    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
    yyj
    -1.73
     海外
    -1.59
    \
    -1.59
    </u>
    -1.54
    嶝
    -1.53
    usahaan
    -1.49
     attributable
    -1.48
     we
    -1.47
     ie
    -1.46
    箆
    -1.45
    POSITIVE LOGITS
    u
    1.59
    ation
    1.59
    糴
    1.55
    🪧
    1.50
    之际
    1.48
    ='',
    1.48
     Ersten
    1.47
    1.45
    過ご
    1.45
    %,
    1.45
    Activations Density 0.023%
    No Known Activations