© 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. 81559
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    This neuron detects numeric year tokens (four-digit dates or reign years) associated with names.

    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
    IZABETH
    -0.80
    xhtml
    -0.79
     pelas
    -0.73
    NUMERIC
    -0.73
    ancier
    -0.71
     Faber
    -0.70
    ться
    -0.69
    ebp
    -0.67
     HAP
    -0.67
    IRIT
    -0.66
    POSITIVE LOGITS
     Delhi
    0.90
    alaya
    0.85
     DELHI
    0.84
    Delhi
    0.84
    řízení
    0.79
     advertising
    0.74
    Neden
    0.74
    lei
    0.73
    nursing
    0.72
    Specifik
    0.72
    Activations Density 0.021%

    No Known Activations