© 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. 65482
    Prev
    Next
    INDEX
    Explanations

    quoted numbers and abbreviations

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

    The neuron fires on numeric tokens (digits, dates, citation superscripts, footnote markers, etc.), i.e. any token containing numbers.

    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
    expiresIn
    -1.96
     our
    -1.77
    汌
    -1.74
     και
    -1.63
    s
    -1.59
    状態で
    -1.58
    隽
    -1.54
     inmediatamente
    -1.51
     diseñ
    -1.48
    resave
    -1.48
    POSITIVE LOGITS
    ógicos
    1.85
    чена
    1.70
     放題
    1.66
     '
    1.66
    )$
    1.53
    蒟
    1.47
     possibility
    1.46
     lament
    1.46
     Anſ
    1.44
    will
    1.42
    Activations Density 0.012%

    No Known Activations