© 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. 10-GEMMASCOPE-RES-131K
    7. 69580
    Prev
    Next
    INDEX
    Explanations

    hours ahead

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

    The neuron detects mentions of “hour,” i.e. time‐duration references using the word hour.

    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
     แต่
    -2.41
    唻
    -2.38
    ܊
    -2.36
     駅前
    -2.31
     houſe
    -2.31
    姈
    -2.22
    ⁧
    -2.17
    Doesn
    -2.17
    onsored
    -2.16
    ,“
    -2.14
    POSITIVE LOGITS
    le
    2.97
    r
    2.92
    ↵↵
    2.84
    on
    2.73
    (
    2.58
    u
    2.55
    to
    2.41
    ?"
    2.39
     we
    2.38
    -"
    2.38
    Activations Density 0.006%

    No Known Activations