© 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. 25619
    Prev
    Next
    INDEX
    Explanations

    MATLAB/Octave code

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

    The neuron is picking out numeric tokens (numbers and number‐containing symbols) in the MATLAB code.

    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
     What
    -0.93
     Both
    -0.90
     Unlike
    -0.89
     what
    -0.84
     literaria
    -0.83
    ၅
    -0.83
     When
    -0.82
    勤務
    -0.82
     fotográfico
    -0.81
     do
    -0.81
    POSITIVE LOGITS
    %
    1.39
     clear
    1.37
    clear
    1.25
     %
    1.16
    fprintf
    1.13
    %%
    1.08
    keyboard
    1.01
     \%
    0.99
    %"
    0.99
     %(
    0.95
    Activations Density 0.002%

    No Known Activations