© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71904
    Prev
    Next
    INDEX
    Explanations

    computational numbers

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

    The neuron responds to standalone numeric tokens (digits or multi‐digit numbers) in mathematical contexts, such as lists of factors, sequences, or numeric answers.

    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
     to
    -2.00
     its
    -1.60
     both
    -1.43
     Both
    -1.42
     up
    -1.41
    Both
    -1.40
    Many
    -1.39
     before
    -1.37
     Bedürfnisse
    -1.34
     itself
    -1.29
    POSITIVE LOGITS
    ྃ
    1.49
     eftersom
    1.32
     firft
    1.31
     gloria
    1.30
    flexGrow
    1.30
    ctory
    1.29
     tornillos
    1.25
     naer
    1.24
     biograf
    1.23
     galeri
    1.22
    Activations Density 0.018%

    No Known Activations