© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29199
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron is keyed to sequences of digits and punctuation forming date/time or version‐style timestamps in logs or diffs.

    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
     Dänemark
    -1.58
     transparentes
    -1.54
    ("");
    
    -1.54
    ;}
    -1.53
    嫋
    -1.52
    ;.
    -1.52
    rdoba
    -1.46
    鲠
    -1.45
     amazingly
    -1.44
     ravaged
    -1.44
    POSITIVE LOGITS
    .
    2.02
     two
    1.63
     over
    1.57
     several
    1.54
    what
    1.51
     three
    1.48
     one
    1.45
    because
    1.45
     just
    1.43
     first
    1.41
    Activations Density 0.012%

    No Known Activations