© 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. 34-GEMMASCOPE-RES-131K
    7. 64629
    Prev
    Next
    INDEX
    Explanations

    ending the day

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

    The neuron flags temporal expressions that specify durations or moments (e.g. “after a long day,” “Friday,” “a hell of a week,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     minuter
    -0.90
     LUNCH
    -0.89
     ida
    -0.88
    👎
    -0.82
     Litu
    -0.80
    ETIME
    -0.79
     malu
    -0.78
     €/
    -0.78
    ✌
    -0.78
     vitam
    -0.77
    POSITIVE LOGITS
     long
    2.17
     tiring
    1.72
     hard
    1.62
     exhausting
    1.59
     busy
    1.51
     dlou
    1.45
     stressful
    1.40
    long
    1.38
     hosszú
    1.34
     taxing
    1.30
    Activations Density 0.024%

    No Known Activations