© 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. 59160
    Prev
    Next
    INDEX
    Explanations

    array functions

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

    The neuron is triggered by code tokens involving array constructs or functions (e.g. “array_…”, “array” keywords).

    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
    ’
    -1.97
    Rarity
    -1.88
    RAID
    -1.80
    鹮
    -1.80
     ليب
    -1.76
     櫃
    -1.73
    饪
    -1.73
    还是要
    -1.70
    ynthetic
    -1.70
     αλλά
    -1.70
    POSITIVE LOGITS
    I
    2.27
    </strong>
    2.22
    :
    2.13
    杙
    2.08
    ...
    1.92
     are
    1.89
    </u>
    1.80
    )
    1.79
    '
    1.79
    1.78
    Activations Density 0.043%

    No Known Activations