© 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. 13410
    Prev
    Next
    INDEX
    Explanations

    bounding box or area

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

    The neuron fires on code tokens that name plotting or formatting parameters (e.g. “par”, “mfrow”, “PlotRange”, “Reset”, “bounding”, “absolute”, “sep”, “inner”)—in other words, configuration‐option keywords.

    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
     receive
    -1.20
    WithMany
    -1.16
     menciona
    -1.13
    ίδι
    -1.10
    september
    -1.09
     увидеть
    -1.08
     sostuvo
    -1.06
     sebagai
    -1.05
     destacado
    -1.05
     negó
    -1.05
    POSITIVE LOGITS
    <bos>
    1.15
     negru
    1.12
     nochmals
    1.09
     nochmal
    1.05
     astu
    1.01
     начина
    0.96
     tatu
    0.96
     exac
    0.95
     kupa
    0.94
    schuhe
    0.93
    Activations Density 0.001%

    No Known Activations