© 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. 111733
    Prev
    Next
    INDEX
    Explanations

    Snack Nation

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

    This neuron fires on technical code tokens—names of developer tools, commands, and programming functions.

    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
    ↵
    -2.48
    la
    -2.19
    The
    -2.16
    {
    -2.13
    ra
    -1.98
    姈
    -1.89
    也不会
    -1.88
    sees
    -1.87
    actéristi
    -1.86
    en
    -1.84
    POSITIVE LOGITS
    ஂ
    2.17
    してました
    2.00
     было
    1.99
    <bos>
    1.92
    medriver
    1.91
    Snackbar
    1.84
    \
    1.80
    ]--;
    1.79
     decreased
    1.78
     важно
    1.77
    Activations Density 0.001%

    No Known Activations