© 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. 10-GEMMASCOPE-RES-131K
    7. 60024
    Prev
    Next
    INDEX
    Explanations

    time phrases

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

    The neuron triggers on words that denote spans or durations of time (e.g. “while,” “time,” “long time”).

    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
     It
    -2.50
    {
    -2.06
     recargable
    -1.64
    namon
    -1.62
    UCION
    -1.59
    Actually
    -1.55
     confronti
    -1.55
     menegaskan
    -1.54
     zmieni
    -1.54
    We
    -1.52
    POSITIVE LOGITS
     ſou
    1.54
    ،
    1.51
     dizaines
    1.51
    角落
    1.50
     HttpNotFound
    1.48
     ее
    1.48
    ，
    1.47
     leur
    1.46
    <>());
    1.46
    StoryboardSegue
    1.45
    Activations Density 0.002%

    No Known Activations