© 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. 34-GEMMASCOPE-RES-131K
    7. 78464
    Prev
    Next
    INDEX
    Explanations

    years followed by punctuation

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

    The neuron fires on numeric reference tokens—i.e. the year‐and‐page (or identifier) numbers in scholarly citations.

    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
     majesty
    -0.80
     Since
    -0.77
     қара
    -0.73
    ்க்க
    -0.72
     terbesar
    -0.71
     aid
    -0.71
    dropIfExists
    -0.71
    CascadeType
    -0.71
     できる
    -0.71
     selama
    -0.71
    POSITIVE LOGITS
    ägg
    1.05
     provenientes
    0.92
    LEIA
    0.91
     surpren
    0.88
     \_
    0.88
     brillantes
    0.88
     imprescin
    0.88
    を感じ
    0.88
    )$,
    0.87
    НЯ
    0.87
    Activations Density 0.004%

    No Known Activations