© 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. 104566
    Prev
    Next
    INDEX
    Explanations

    as soon as

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

    This neuron detects adverbial phrases that mark immediate temporal succession (e.g. “as soon as,” “the moment,” “immediately upon”).

    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
    ONLY
    -1.30
     seulement
    -1.26
     only
    -1.26
    桖
    -1.25
     uniquement
    -1.22
     فقط
    -1.21
     trayectoria
    -1.20
    Later
    -1.19
    later
    -1.18
    gesamt
    -1.17
    POSITIVE LOGITS
     into
    1.41
     those
    1.30
     it
    1.28
     starts
    1.27
     begins
    1.25
     before
    1.23
     started
    1.23
     any
    1.20
     Sobald
    1.19
     off
    1.16
    Activations Density 0.021%

    No Known Activations