© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129922
    Prev
    Next
    INDEX
    Explanations

    The neuron is keying on long numeric timestamp strings (e.g. “created_at” ISO-style dates and time-zone offsets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    telephone calls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     for
    -1.73
     in
    -1.41
     from
    -1.28
     will
    -1.22
     at
    -1.16
     high
    -1.16
     all
    -1.10
     started
    -1.10
     until
    -1.09
     FOR
    -1.09
    POSITIVE LOGITS
     publier
    1.50
     affez
    1.41
     osoba
    1.38
     produrre
    1.34
     réserver
    1.34
     sensazione
    1.34
    Weiterlesen
    1.30
     meninos
    1.30
     colorear
    1.29
     лента
    1.29
    Activations Density 0.000%

    No Known Activations