© 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. 84174
    Prev
    Next
    INDEX
    Explanations

    gathering information or ideas

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

    The neuron fires on occurrences of the verb “gather” (including its inflected forms like “gathered”) and nearby collection phrases.

    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
    𓋼
    -2.67
    you
    -2.14
    =
    -1.93
    糴
    -1.92
    IMUM
    -1.90
     transacción
    -1.88
    榈
    -1.84
    ↵
    -1.77
    including
    -1.73
    ᓚ
    -1.73
    POSITIVE LOGITS
    ?
    2.05
    有一定
    1.75
     first
    1.72
     fled
    1.70
    に関して
    1.70
     imprescindible
    1.66
     ‘‘
    1.64
    大半
    1.60
     his
    1.58
    
    1.57
    Activations Density 0.011%

    No Known Activations