© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65143
    Prev
    Next
    INDEX
    Explanations

    plot or collection

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

    The neuron strongly activates on code identifier fragments—especially private/internal helper function or parameter names marked by underscores (e.g. parts of `_add_colorbar`, `_infer_interval_breaks`, `_process_cmap_cbar_`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     diamètre
    -0.74
    lium
    -0.74
     ancien
    -0.73
     Volk
    -0.73
     curvas
    -0.72
     bể
    -0.72
     bakım
    -0.71
    𝑳
    -0.69
    axis
    -0.69
     профилакти
    -0.68
    POSITIVE LOGITS
     cmap
    1.51
    cmap
    1.09
    extent
    0.90
     extent
    0.88
     CM
    0.82
     快
    0.80
    androidx
    0.79
    訓
    0.78
     CCM
    0.78
    CM
    0.76
    Activations Density 0.009%

    No Known Activations