© 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. 19793
    Prev
    Next
    INDEX
    Explanations

    describing states or actions

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

    The neuron flags temporal expressions—mentions of dates, times, durations, ages, parts of the day, etc.

    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
    ragende
    -1.34
    below
    -1.31
    いつ
    -1.28
    ཿ
    -1.28
     kesel
    -1.26
    を使う
    -1.22
    certainly
    -1.20
    almost
    -1.20
    hacer
    -1.20
    later
    -1.19
    POSITIVE LOGITS
     to
    1.36
     but
    1.23
    ūrė
    1.20
     relatively
    1.14
     or
    1.14
     specific
    1.13
     some
    1.10
     two
    1.09
    乃至
    1.09
    educt
    1.08
    Activations Density 0.250%

    No Known Activations