© 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. 34-GEMMASCOPE-RES-131K
    7. 2010
    Prev
    Next
    INDEX
    Explanations

    PC PCA PCD

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

    The neuron strongly activates on numeric tokens (sequences of digits) in the text.

    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
    PSP
    -0.74
     psp
    -0.72
    斗争
    -0.70
     Stony
    -0.69
    刚好
    -0.68
     Swartz
    -0.68
    LPS
    -0.66
    ಛ
    -0.66
    omena
    -0.65
     Chesterfield
    -0.65
    POSITIVE LOGITS
     PC
    5.13
    PC
    4.63
     pc
    4.50
    pc
    4.41
     PCs
    3.83
     Pc
    3.58
    Pc
    3.55
    PCs
    3.52
     PCA
    3.27
     PCS
    3.03
    Activations Density 0.068%

    No Known Activations