© 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. 90383
    Prev
    Next
    INDEX
    Explanations

    multiples and ratios quantified

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

    The neuron activates on numeric tokens and digits (i.e. actual numbers or number‐related sequences).

    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
    Twice
    -1.34
     Twice
    -1.31
    twice
    -1.26
     twice
    -1.13
     twofold
    -1.11
     TWICE
    -1.02
    Half
    -1.02
     Hälfte
    -1.00
     half
    -0.97
    half
    -0.94
    POSITIVE LOGITS
     ten
    1.29
     hundred
    1.13
    ten
    1.00
     Ten
    0.99
     thousand
    0.94
     TEN
    0.89
    ×
    0.82
    ASTNode
    0.81
     twenty
    0.80
     Deb
    0.79
    Activations Density 0.052%

    No Known Activations