© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16591
    Prev
    Next
    INDEX
    Explanations

    states of being and consequences

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

    The neuron activates on numeric tokens representing quantitative values (e.g., dosages, measurements, counts).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     panik
    -1.58
     tirs
    -1.55
     teka
    -1.54
     disiplin
    -1.51
     kriminal
    -1.49
     pandemi
    -1.48
     ekster
    -1.48
     risiko
    -1.47
     aktivi
    -1.45
     dolar
    -1.45
    POSITIVE LOGITS
     help
    1.44
     helpful
    1.43
     schönes
    1.38
     used
    1.35
     a
    1.35
     useful
    1.28
     fueron
    1.27
     helps
    1.26
     able
    1.23
     sujeito
    1.22
    Activations Density 0.112%

    No Known Activations