© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15677
    Prev
    Next
    INDEX
    Explanations

    ggplot geom_point and enter append

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

    The neuron fires on ggplot2 “geom_” function calls (tokens beginning with “geom_”).

    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
    валя
    -1.32
     saada
    -1.20
     võib
    -1.13
    倹
    -1.13
    kuwa
    -1.12
     tahu
    -1.11
    InputBorder
    -1.11
     its
    -1.11
    Reentrant
    -1.11
     adatta
    -1.08
    POSITIVE LOGITS
    ,
    1.25
     additions
    1.04
     after
    1.03
    ным
    1.00
     lamentable
    0.99
    0.99
     castel
    0.97
    横浜
    0.96
    福岡
    0.94
    种类
    0.92
    Activations Density 0.001%
    No Known Activations