© 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. 75480
    Prev
    Next
    INDEX
    Explanations

    filler text repetition

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

    This neuron detects sequences of repeated filler or exclamatory tokens (e.g. “blah blah blah,” “very very very,” “yeah yeah yeah,” “na na na”) used for emphasis.

    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
     to
    -1.58
     another
    -1.42
    だか
    -1.34
     doenças
    -1.22
     интел
    -1.20
     various
    -1.20
    进行
    -1.20
     again
    -1.17
    ませて
    -1.16
    DESCRIPCIÓN
    -1.14
    POSITIVE LOGITS
    ’
    1.55
    {~
    1.49
     —
    1.48
     Kläger
    1.34
     “(
    1.34
    .”
    1.30
    icamente
    1.30
    ”、“
    1.29
     будешь
    1.28
    itarios
    1.27
    Activations Density 0.033%

    No Known Activations