© 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. 7560
    Prev
    Next
    INDEX
    Explanations

    Mac

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

    The neuron is highly selective for the standalone token “Mac” whenever it 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
    lgari
    -2.92
    ឵
    -2.63
    öpfer
    -2.53
    場所に
    -2.47
    狍
    -2.47
    饃
    -2.39
     soñ
    -2.38
     lojas
    -2.36
    ところは
    -2.34
     และ
    -2.33
    POSITIVE LOGITS
    ’
    3.47
    y
    3.44
    \
    3.03
    u
    2.75
    2.52
    的
    2.50
    The
    2.45
     {
    2.44
    }
    2.44
    ar
    2.41
    Activations Density 0.013%

    No Known Activations