© 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. 71350
    Prev
    Next
    INDEX
    Explanations

    remind or reminder prompts

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

    The neuron activates on occurrences of “remind” and its morphological variants (e.g. “reminder,” “reminding”).

    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
    s
    -3.41
    2
    -3.38
    4
    -3.17
    6
    -2.59
    3
    -2.56
    D
    -2.53
    8
    -2.52
    5
    -2.42
     avec
    -2.41
     pero
    -2.41
    POSITIVE LOGITS
     camiset
    2.63
     Sociedade
    2.45
     forro
    2.41
    鸶
    2.41
    蘩
    2.36
    縯
    2.36
     火鍋
    2.31
     eléct
    2.31
     parís
    2.30
     incess
    2.25
    Activations Density 0.003%

    No Known Activations