© 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. 34-GEMMASCOPE-RES-131K
    7. 117343
    Prev
    Next
    INDEX
    Explanations

    hour ahead or behind

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

    This neuron fires on occurrences of the token “hour” (including “Hour” or “Hours”), i.e. mentions of hours as time markers in logs or 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_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
    months
    -1.10
     बाहर
    -1.07
     days
    -1.06
    Months
    -1.06
    濛
    -1.05
     months
    -1.04
    izzare
    -1.02
     Desserts
    -0.99
     días
    -0.98
    呃
    -0.98
    POSITIVE LOGITS
     of
    1.69
     работы
    1.37
    long
    1.06
    .
    1.05
    maid
    1.05
    lang
    1.04
     langer
    0.94
     flight
    0.92
    ⏰
    0.92
    cast
    0.90
    Activations Density 0.024%

    No Known Activations