© 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. 22-GEMMASCOPE-RES-131K
    7. 33274
    Prev
    Next
    INDEX
    Explanations

    time units

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

    The main thing this neuron does is find words denoting time periods or parts of the day (e.g. morning, weekend, week, year).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    sightly
    -1.15
     such
    -1.13
     or
    -1.08
     ilyen
    -1.06
     a
    -1.05
     during
    -0.96
     während
    -0.96
     隊
    -0.96
    這種
    -0.92
     tätig
    -0.92
    POSITIVE LOGITS
     vetorial
    1.05
     Categoria
    1.03
    mappedBy
    1.01
     Möglichkeit
    1.01
    curriculum
    1.00
    oğlu
    0.99
     fluide
    0.99
    andExpect
    0.99
     LIND
    0.97
     experiences
    0.96
    Activations Density 0.030%

    No Known Activations