© 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. 9992
    Prev
    Next
    INDEX
    Explanations

    times with am or pm

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

    The neuron strongly activates on numeric tokens representing times (hours and minutes) in schedules.

    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
    1
    -2.55
    3
    -2.44
    4
    -2.31
    幾個
    -1.90
    5
    -1.86
    兩個
    -1.85
    They
    -1.84
    𓁹
    -1.84
    できるだけ
    -1.80
    6
    -1.80
    POSITIVE LOGITS
    </i>
    2.48
    </sub>
    2.00
    dė
    1.91
     eſſ
    1.84
    )’
    1.84
    ↵
    1.80
    mafia
    1.80
    ͗
    1.80
    kurtka
    1.80
    sukienka
    1.77
    Activations Density 0.015%

    No Known Activations