© 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. 34-GEMMASCOPE-RES-131K
    7. 6873
    Prev
    Next
    INDEX
    Explanations

    standings and results

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

    This neuron is strongly activated by numeric tokens (years, version numbers, counts, and other digit sequences).

    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
    !!!!
    -0.77
    lijden
    -0.77
     contamin
    -0.75
     खरी
    -0.75
     delinqu
    -0.74
     idolat
    -0.71
     CUN
    -0.71
    iu
    -0.70
     approbation
    -0.67
     поши
    -0.67
    POSITIVE LOGITS
    WaitFor
    0.88
    burner
    0.86
     станции
    0.82
     filhos
    0.79
     fatos
    0.77
     recub
    0.77
     STATION
    0.76
    chandra
    0.75
    baly
    0.75
     RED
    0.74
    Activations Density 0.004%

    No Known Activations