© 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. 111767
    Prev
    Next
    INDEX
    Explanations

    units of time

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

    This neuron responds to explicit numerical measurements—especially time durations like days, hours, and minutes, often including decimal values.

    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
    :
    -1.20
    átka
    -1.19
    Ї
    -1.08
    artney
    -1.08
     desempen
    -1.06
     СМИ
    -1.05
    𝗉
    -1.05
     Zähne
    -1.05
    úst
    -1.03
    ブリッド
    -1.03
    POSITIVE LOGITS
    lagten
    1.17
    さまざまな
    1.13
     merusak
    1.12
     ajang
    1.07
     platt
    1.05
     impon
    1.05
     mengumumkan
    1.05
    ctility
    1.05
    ="
    1.05
     quieres
    1.03
    Activations Density 0.223%

    No Known Activations