© 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. 69850
    Prev
    Next
    INDEX
    Explanations

    years, weeks, days, months

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

    The neuron responds to temporal unit words (like “années,” “曜日/星期,” “dia,” “Edizione,” etc.), i.e. names of time divisions in various languages.

    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
     lepší
    -2.38
    猹
    -2.13
    そして
    -2.08
     sebagainya
    -2.08
     verhind
    -1.88
     ponga
    -1.88
    尨
    -1.88
    ⃢
    -1.87
     GALERÍA
    -1.86
    ciutto
    -1.84
    POSITIVE LOGITS
    )
    2.98
    en
    2.83
    le
    2.50
    L
    2.25
    ze
    1.95
    er
    1.92
    times
    1.92
     last
    1.91
    人們
    1.91
    providedIn
    1.86
    Activations Density 0.001%

    No Known Activations