© 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. 34-GEMMASCOPE-RES-131K
    7. 58906
    Prev
    Next
    INDEX
    Explanations

    code and punctuation separators

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

    The neuron strongly activates on numeric tokens or tokens containing digits (e.g. years, scores, version numbers, numeric literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     cartridges
    -0.74
     cartridge
    -0.72
    eramente
    -0.71
     сель
    -0.69
     breeds
    -0.69
    jection
    -0.69
    珥
    -0.68
    entially
    -0.68
     Inscription
    -0.68
    entis
    -0.67
    POSITIVE LOGITS
     svoj
    0.71
     Thong
    0.70
    電源
    0.65
     elab
    0.65
    зан
    0.63
    ₭
    0.62
     Initialise
    0.62
    他还
    0.61
    Ồ
    0.60
    ksz
    0.59
    Activations Density 0.085%

    No Known Activations