© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11670
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron strongly activates on numeric digit tokens (i.e. parts of 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
    他们
    -1.98
    𞤢
    -1.55
    Aktu
    -1.53
     آنان
    -1.48
     チラ
    -1.47
    Aktuelle
    -1.44
    netje
    -1.40
    ᜀ
    -1.40
    Interess
    -1.38
     libras
    -1.34
    POSITIVE LOGITS
     also
    2.09
     шапка
    1.92
     there
    1.71
     another
    1.63
     I
    1.62
     in
    1.54
    𐑂
    1.51
     through
    1.45
     along
    1.45
     включает
    1.41
    Activations Density 0.022%

    No Known Activations