© 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. 27924
    Prev
    Next
    INDEX
    Explanations

    forum thread titles

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

    This neuron detects “Re:” reply headers followed by numeric identifiers.

    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
     MERCHANTABILITY
    -1.41
     estekak
    -1.36
    ᑎ
    -1.27
    haviours
    -1.23
     feitas
    -1.21
     silnika
    -1.20
     gången
    -1.19
    готовки
    -1.17
     PUSTAKA
    -1.17
     przód
    -1.17
    POSITIVE LOGITS
    u
    1.40
     questions
    1.20
    1.09
     and
    1.05
    ar
    1.05
    ,
    1.00
    多少钱
    0.98
     /
    0.98
     --
    0.97
    嗆
    0.96
    Activations Density 0.003%

    No Known Activations