© 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. 103916
    Prev
    Next
    INDEX
    Explanations

    stick to / with

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

    The neuron fires on occurrences of the phrase “stick to” (i.e. the idiomatic “stick to X”).

    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
     facto
    -1.37
     "
    -1.27
    ならず
    -1.26
     autre
    -1.26
    FINED
    -1.24
     ceci
    -1.23
    頭を
    -1.23
     attributable
    -1.23
     diesem
    -1.23
     этим
    -1.21
    POSITIVE LOGITS
     what
    1.39
    ഒ
    1.39
     blanda
    1.38
    لقد
    1.36
     hvem
    1.34
    ta
    1.33
     recommended
    1.29
    ot
    1.29
     guidelines
    1.27
     suggest
    1.27
    Activations Density 0.013%

    No Known Activations