© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73908
    Prev
    Next
    INDEX
    Explanations

    times of day

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

    This neuron detects mentions of times of day (e.g., “morning,” “night,” “afternoon”).

    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
     that
    -1.95
     a
    -1.65
    no
    -1.48
    at
    -1.46
     not
    -1.41
    TE
    -1.39
    us
    -1.34
    T
    -1.33
    ate
    -1.33
     can
    -1.32
    POSITIVE LOGITS
    Preparazione
    1.43
     phê
    1.41
    ارتمان
    1.38
    質感
    1.36
    本田
    1.30
    🕗
    1.30
     thánh
    1.28
    ⡪
    1.28
    狛
    1.27
     adresu
    1.27
    Activations Density 0.012%

    No Known Activations