© 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. 48293
    Prev
    Next
    INDEX
    Explanations

    sixth in rank or sequence

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

    The neuron strongly activates on the ordinal “sixth” (e.g. sixth-grade, Sixth Circuit), i.e. ordinal numbers ending in “th.”

    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
    ⟞
    -2.91
     &
    -2.73
    “
    -2.55
     was
    -2.53
     ‘
    -2.47
    ’,
    -2.45
    垍
    -2.36
    嫱
    -2.34
     ‘‘
    -2.34
    亖
    -2.31
    POSITIVE LOGITS
     prévue
    2.88
    If
    2.80
    礦
    2.59
    
    2.58
    可能
    2.56
    ilihan
    2.55
    Продам
    2.48
    t
    2.45
    ｇ
    2.45
    埸
    2.41
    Activations Density 0.023%

    No Known Activations