© 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. 79514
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    This neuron detects mentions of dates or temporal expressions, especially month names paired with numbers (e.g., “March 604,” “October 572,” “June 510”).

    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
     during
    -1.18
     before
    -1.06
     and
    -1.06
     last
    -0.98
     through
    -0.94
     written
    -0.93
     since
    -0.91
    其他的
    -0.90
    clés
    -0.85
    ++];
    -0.84
    POSITIVE LOGITS
     demandes
    1.20
     tentatively
    0.96
     žá
    0.95
     proposent
    0.90
    reached
    0.89
     remoto
    0.88
     peines
    0.86
    revealed
    0.86
     fået
    0.85
    wegen
    0.84
    Activations Density 0.035%

    No Known Activations