© 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. 44357
    Prev
    Next
    INDEX
    Explanations

    day-to-day activities

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

    This neuron detects occurrences of the phrase “day-to-day” (the repetitive “day” in a day-to-day context).

    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
    -2.25
    vgili
    -2.05
    omores
    -2.02
     When
    -1.90
     Apparently
    -1.77
    </b>
    -1.74
     Another
    -1.72
     While
    -1.68
     Shortly
    -1.65
    選べる
    -1.64
    POSITIVE LOGITS
    ra
    2.27
    an
    2.08
    f
    2.05
    ing
    2.02
     幅
    1.93
    ri
    1.90
     them
    1.87
     helg
    1.86
     quei
    1.82
    ଽ
    1.82
    Activations Density 0.004%

    No Known Activations