© 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. 99933
    Prev
    Next
    INDEX
    Explanations

    numbers one and two

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

    The neuron activates on standalone numeric tokens and digit-based identifiers (e.g. version or chapter numbers, IDs) in technical 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_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
    穑
    -1.83
     tüm
    -1.76
     devenue
    -1.75
     stik
    -1.73
    出了一
    -1.73
    
    -1.72
     diriger
    -1.70
     เขา
    -1.67
     knop
    -1.66
    臜
    -1.66
    POSITIVE LOGITS
     such
    2.20
     they
    2.09
     you
    2.05
     different
    1.95
    and
    1.73
     these
    1.66
     those
    1.66
     various
    1.63
     including
    1.62
     previous
    1.60
    Activations Density 0.001%

    No Known Activations