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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75109
    Prev
    Next
    INDEX
    Explanations

    writing and creating books

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

    The main thing this neuron does is find numeric tokens (i.e. numbers or digits) 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_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
     their
    -1.30
     they
    -1.23
    their
    -1.20
    tablissements
    -1.14
     jede
    -1.13
     staff
    -1.11
     service
    -1.09
    趨
    -1.06
     participation
    -1.06
     services
    -1.06
    POSITIVE LOGITS
     crochê
    1.52
     Bemerkungen
    1.47
     my
    1.32
     manuscript
    1.30
    providedIn
    1.27
     Características
    1.27
    ulación
    1.23
     about
    1.23
     ancak
    1.22
     projektu
    1.20
    Activations Density 0.044%

    No Known Activations