© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128075
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric tokens and numeric references (e.g. years, section or case numbers, statistics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    foreign words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     as
    -0.99
     all
    -0.94
     using
    -0.91
    顶
    -0.85
     these
    -0.82
     so
    -0.81
     become
    -0.80
     out
    -0.79
     upon
    -0.79
     on
    -0.78
    POSITIVE LOGITS
    鲑
    1.01
     Standardi
    0.88
    こない
    0.87
    θρω
    0.85
     cheques
    0.85
    ÜN
    0.84
    dotti
    0.84
    精密
    0.84
    ARIOS
    0.84
     condoms
    0.84
    Activations Density 0.014%

    No Known Activations