© 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. 67054
    Prev
    Next
    INDEX
    Explanations

    reviews and dates

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

    The neuron detects date- and time-related metadata (e.g. calendar dates, “X days ago” timestamps, review dates).

    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
    
    -1.37
     provocando
    -1.36
     потім
    -1.36
    ༩
    -1.36
     墊
    -1.30
    鯪
    -1.29
    気に入りの
    -1.27
     inflación
    -1.25
     пър
    -1.24
     тази
    -1.24
    POSITIVE LOGITS
    荜
    1.45
    ,’
    1.43
     resulta
    1.42
     only
    1.36
     always
    1.35
     siempre
    1.31
    there
    1.31
     результа
    1.30
     any
    1.29
    pgfmath
    1.29
    Activations Density 0.027%

    No Known Activations