© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23643
    Prev
    Next
    INDEX
    Explanations

    code, like MATLAB or Python plotting

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

    The neuron fires on references to MATLAB’s GUIDE GUI-building environment and its callback‐type specifications.

    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
     Scripts
    -0.85
     scripts
    -0.81
    Companion
    -0.80
     EMI
    -0.74
     Companion
    -0.74
    Discus
    -0.70
    telefono
    -0.70
     Rend
    -0.70
     centenary
    -0.70
     core
    -0.69
    POSITIVE LOGITS
    gcf
    1.16
    gca
    1.14
     axes
    1.06
    findall
    0.99
    Axes
    0.97
    find
    0.93
     ancestor
    0.90
     Axes
    0.89
     get
    0.89
     figure
    0.88
    Activations Density 0.008%

    No Known Activations