© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73700
    Prev
    Next
    INDEX
    Explanations

    code delimiters or special characters

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

    The neuron is primarily responding to numeric tokens (i.e. standalone numbers and digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     både
    -0.98
     komentar
    -0.95
    нулась
    -0.93
    花粉
    -0.93
     nombreux
    -0.92
    <bos>
    -0.91
     ещё
    -0.91
    kamers
    -0.88
     thermique
    -0.88
    嘿嘿
    -0.87
    POSITIVE LOGITS
     other
    0.95
     which
    0.91
     without
    0.91
     their
    0.91
     specifically
    0.89
     vilja
    0.88
    GRAFÍA
    0.86
     there
    0.84
    </h1>
    0.84
    AL
    0.84
    Activations Density 0.118%

    No Known Activations