© 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. 102337
    Prev
    Next
    INDEX
    Explanations

    printing cricuit, Lady Gaga, lung disease

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

    The neuron is flagging isolated or unusually segmented tokens that correspond to acronyms, single-letter identifiers, or proper names (e.g. “K,” “c” in “circuit,” “Brotherly,” “guy”).

    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
     which
    -1.42
     primeiro
    -1.35
     AFTER
    -1.22
     longo
    -1.20
     después
    -1.20
     then
    -1.20
     after
    -1.19
    ଃ
    -1.18
     bisherigen
    -1.18
     since
    -1.18
    POSITIVE LOGITS
     Âge
    1.15
     Etats
    1.13
    Projek
    1.11
    ⅔
    1.07
    سپ
    1.06
    mögen
    1.05
    ساز
    1.04
    𝐺
    1.03
    жаю
    1.02
     boîtes
    1.00
    Activations Density 0.339%

    No Known Activations