© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    expressing or writing out text

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

    The neuron is essentially a detector for the token “out,” firing strongly whenever that exact word appears.

    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
    [
    -2.06
    </b>
    -2.06
    \
    -2.03
    --
    -1.99
    <
    -1.98
    \\
    -1.93
    </
    -1.84
    ​
    -1.84
    2
    -1.72
    {
    -1.71
    POSITIVE LOGITS
    褙
    2.14
    丏
    1.96
    widual
    1.92
    苙
    1.88
    僂
    1.82
     apetito
    1.78
     cuarent
    1.78
    》,
    1.77
    緜
    1.76
    ☡
    1.75
    Activations Density 0.007%

    No Known Activations