© 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. 107562
    Prev
    Next
    INDEX
    Explanations

    Standard Model extensions

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

    This neuron specializes in spotting numeric identifiers and codes (e.g. preprint numbers, years, arXiv IDs) within the document.

    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
    Videos
    -0.82
     ||=
    -0.81
    ʞ
    -0.79
    ORDIN
    -0.79
     throwback
    -0.79
    jaro
    -0.79
     позже
    -0.78
     arXiv
    -0.77
     kepercayaan
    -0.74
    avyzd
    -0.74
    POSITIVE LOGITS
     errors
    0.93
     latex
    0.83
     Ather
    0.81
     nogle
    0.80
     use
    0.80
    ydney
    0.75
     reaper
    0.74
    𝜃
    0.74
    Latex
    0.73
    inete
    0.73
    Activations Density 0.008%

    No Known Activations