© 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. 40385
    Prev
    Next
    INDEX
    Explanations

    Other, selected, former, few

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

    This neuron specifically fires on the word “Other” (as used to introduce list/section headings).

    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
     their
    -1.59
     on
    -1.41
     both
    -1.31
     most
    -1.22
     each
    -1.20
     only
    -1.19
     this
    -1.16
     all
    -1.15
     started
    -1.11
     every
    -1.09
    POSITIVE LOGITS
    logii
    1.40
    imiento
    1.38
     uttry
    1.29
     урока
    1.20
     transparentes
    1.19
    готовка
    1.17
     bekym
    1.17
    ᄎ
    1.15
    犟
    1.15
     шапка
    1.15
    Activations Density 0.004%

    No Known Activations