© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21948
    Prev
    Next
    INDEX
    Explanations

    c followed by symbols or powers

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

    The neuron fires on occurrences of the single‐letter code identifier “c.”

    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
    ၟ
    -3.19
    quelize
    -3.09
     itſelf
    -3.02
    釔
    -2.86
    輓
    -2.86
    in
    -2.84
    tembro
    -2.80
     voor
    -2.73
    izoen
    -2.73
    iciais
    -2.69
    POSITIVE LOGITS
    0
    3.14
    '
    3.14
     \
    3.11
    /
    2.92
    If
    2.84
     &
    2.66
    -
    2.59
    *
    2.56
    "
    2.55
    9
    2.53
    Activations Density 0.055%

    No Known Activations