© 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. 87359
    Prev
    Next
    INDEX
    Explanations

    quantifiers like all, both, each, rest

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

    The neuron responds to the character sequence “alle” (in any casing) occurring within a word.

    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
    Ꮫ
    -2.73
    
    -2.53
     belangrijk
    -2.48
    镲
    -2.44
    ’
    -2.36
    replacing
    -2.19
    臜
    -2.19
     moeili
    -2.19
     แต่
    -2.19
     ſta
    -2.14
    POSITIVE LOGITS
     There
    2.97
     Both
    2.77
     Each
    2.45
     This
    2.33
     Making
    2.31
    Both
    2.28
    !!!!!
    2.25
    ؛
    2.23
    「
    2.23
    There
    2.22
    Activations Density 0.002%

    No Known Activations