© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13240
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron strongly activates on numeric tokens (digit sequences), especially numbers appearing in dates or other numeric fields.

    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
     інші
    -1.60
    :
    -1.59
     for
    -1.57
     kiti
    -1.57
    !
    -1.52
     beve
    -1.48
    などを
    -1.44
    涐
    -1.35
     lantaran
    -1.34
     elek
    -1.33
    POSITIVE LOGITS
     it
    2.78
     necesite
    1.71
     funcione
    1.59
    чностью
    1.55
     haga
    1.53
     sabias
    1.48
    спомина
    1.47
     seleccione
    1.45
     encuentre
    1.45
    </h4>
    1.45
    Activations Density 0.035%

    No Known Activations