© 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. 71435
    Prev
    Next
    INDEX
    Explanations

    words followed by 'is'

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

    This neuron strongly activates on words at the beginnings of lines or verses in song lyrics.

    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
    וּ
    -1.32
    Моя
    -1.26
    Тел
    -1.25
    极为
    -1.21
     peluche
    -1.20
     Secrétaire
    -1.20
     pihaknya
    -1.19
     pêche
    -1.16
     évé
    -1.16
     Ministre
    -1.16
    POSITIVE LOGITS
     to
    1.61
    ’
    1.32
     τὴν
    1.25
     never
    1.13
     ninety
    1.09
     shed
    1.08
     <",
    1.08
    mnop
    1.07
     τὸν
    1.07
     enough
    1.06
    Activations Density 0.028%

    No Known Activations