© 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. 34-GEMMASCOPE-RES-131K
    7. 106713
    Prev
    Next
    INDEX
    Explanations

    anytime and at any time

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

    The neuron activates on indefinite quantifier words and related prepositions (e.g. “any,” “at,” “anywhere”) that signal unrestricted time or place.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ziała
    -0.91
     noong
    -0.84
    為に
    -0.79
     miej
    -0.73
    ığ
    -0.72
    жо
    -0.71
     nhat
    -0.71
    ../../
    -0.71
     recursively
    -0.70
    ulex
    -0.70
    POSITIVE LOGITS
     anytime
    6.97
    Anytime
    5.00
     Anytime
    4.91
    随时
    4.09
     jederzeit
    3.94
     any
    3.30
    隨時
    3.27
    いつでも
    3.25
     любое
    3.16
     whenever
    2.98
    Activations Density 0.101%

    No Known Activations