© 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. 368
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    This neuron fires on multi‐letter subword fragments of content words (i.e. meaningful word stems or prefixes) rather than on common function words.

    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
    There
    -1.98
    でしょうね
    -1.65
    In
    -1.64
    Surprisingly
    -1.56
    Another
    -1.56
    One
    -1.51
    For
    -1.49
    When
    -1.48
    After
    -1.45
    Some
    -1.43
    POSITIVE LOGITS
    𓁹
    1.68
    ⮑
    1.67
    olge
    1.63
    atized
    1.63
    珰
    1.61
     señalado
    1.60
     diferentes
    1.58
    eload
    1.56
    になるので
    1.55
    oneof
    1.54
    Activations Density 0.075%

    No Known Activations