© 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. 102969
    Prev
    Next
    INDEX
    Explanations

    predecessor and predecessors

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

    The neuron selectively activates on digit‐only tokens or numeric sequences, effectively detecting numbers wherever they appear.

    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
    ตอน
    -0.84
    Booking
    -0.77
    ürd
    -0.75
    Originally
    -0.74
    ફ
    -0.72
    Bottom
    -0.72
    lifecycle
    -0.71
    浮现
    -0.70
     Jeg
    -0.69
    ರೆ
    -0.69
    POSITIVE LOGITS
     predecessor
    5.69
     predecessors
    4.91
    prede
    4.03
     preceding
    3.70
     precursor
    3.66
    Prede
    3.53
     precursors
    3.23
     Vorg
    3.05
     precede
    3.02
    前
    3.02
    Activations Density 0.078%

    No Known Activations