© 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. 34-GEMMASCOPE-RES-131K
    7. 30954
    Prev
    Next
    INDEX
    Explanations

    the [place/time]

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

    The neuron specifically responds to multi-digit numeric tokens (e.g. four-digit numbers) 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
    <bos>
    -1.02
    rophi
    -0.97
     gjort
    -0.96
    三个
    -0.95
    lifting
    -0.89
    椿
    -0.88
     على
    -0.88
    tial
    -0.86
    gap
    -0.84
     conversación
    -0.84
    POSITIVE LOGITS
     behalf
    1.83
     heels
    1.63
     basis
    1.59
     sidelines
    1.52
     verge
    1.50
     outskirts
    1.45
     cusp
    1.41
     same
    1.39
     occasions
    1.33
     doorstep
    1.30
    Activations Density 0.093%

    No Known Activations