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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71433
    Prev
    Next
    INDEX
    Explanations

    December dates and numbers

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

    The neuron detects document date stamps—numeric month/day (and sometimes year) sequences (e.g. “Dec 12, 2009”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     nehmen
    -2.16
    }
    -2.09
     puede
    -2.02
     zealous
    -2.02
     deafening
    -2.00
     dejected
    -1.94
     myriad
    -1.91
     merciless
    -1.90
    brtc
    -1.90
     bestimmte
    -1.85
    POSITIVE LOGITS
    蕺
    2.06
    芣
    1.94
    砗
    1.82
    ଫ
    1.76
     and
    1.76
     AUSTRALIA
    1.76
     ?',
    1.72
     GERMANY
    1.67
     Danmark
    1.66
     todav
    1.64
    Activations Density 0.051%

    No Known Activations