© 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. 85345
    Prev
    Next
    INDEX
    Explanations

    zi zipper

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

    The neuron spikes whenever it sees the character sequence “zip” (and its morphological variants) in a word or token.

    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
    n
    -3.41
    The
    -3.31
    ↵
    -2.83
    a
    -2.77
    i
    -2.73
    to
    -2.61
    which
    -2.53
    at
    -2.45
    t
    -2.45
    on
    -2.44
    POSITIVE LOGITS
     \&
    2.73
    ライター
    2.56
    罍
    2.42
     évaluation
    2.39
    zi
    2.33
     ก็
    2.30
    ꯷
    2.30
    蚨
    2.28
    鋱
    2.27
    ."
    2.25
    Activations Density 0.004%

    No Known Activations