© 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. 45155
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

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

    This neuron fires on long runs of non-letter punctuation (e.g. many `*` in a comment border or a standalone `.`), i.e. sequences of repeated punctuation characters.

    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
    -
    -2.63
    In
    -2.55
    </b>
    -2.52
     "
    -2.38
    </u>
    -2.31
    7
    -2.27
    /*
    -2.25
    s
    -2.17
    -2.08
    5
    -2.02
    POSITIVE LOGITS
    豨
    2.33
    䡲
    1.97
    arangay
    1.92
    chiha
    1.90
     diamants
    1.88
    ⵎ
    1.88
    voices
    1.87
     аккура
    1.85
     dangere
    1.84
    眩
    1.81
    Activations Density 0.002%

    No Known Activations