© 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. 22-GEMMASCOPE-RES-131K
    7. 35457
    Prev
    Next
    INDEX
    Explanations

    large quantities of people or items

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

    The neuron strongly activates on numeric tokens—i.e. quantities, years, counts, and other numbers in a document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     that
    -1.36
     after
    -1.16
     but
    -1.09
     is
    -1.09
     or
    -1.05
     only
    -1.02
     seulement
    -0.98
    iramente
    -0.97
     ruh
    -0.96
     should
    -0.94
    POSITIVE LOGITS
     통해
    1.34
     através
    1.24
     across
    1.22
     families
    1.20
    through
    1.18
     côn
    1.16
    ỡi
    1.15
    enterOuterAlt
    1.14
     bezpośrednio
    1.13
     pomaga
    1.09
    Activations Density 0.016%

    No Known Activations