© 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. 12740
    Prev
    Next
    INDEX
    Explanations

    four-digit numbers

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

    The neuron selectively activates on multi-digit numeric tokens (e.g. three- or four-digit 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
    In
    -3.67
    ?
    -2.44
    e
    -2.31
     Vertreter
    -2.27
    O
    -2.08
    ٨
    -2.00
     eds
    -1.91
     interessieren
    -1.87
     a
    -1.86
    了一个
    -1.84
    POSITIVE LOGITS
     sinyal
    2.50
    кономі
    2.30
     dekoratif
    2.19
    轵
    2.14
     dévelo
    2.09
    嚒
    2.09
    ቷ
    2.03
    ፳
    2.03
    蔟
    2.00
    鸶
    1.99
    Activations Density 0.014%

    No Known Activations