© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6159
    Prev
    Next
    INDEX
    Explanations

    MATLAB comments and commands

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

    The neuron responds to tokens representing precise numerical measurements (especially decimal‐formatted numbers and percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .#
    0.93
     #
    0.93
    ,#
    0.78
     {#
    0.75
     (#
    0.74
    {#
    0.70
    -#
    0.70
    +#
    0.69
     +#
    0.69
    (#
    0.68
    POSITIVE LOGITS
    %
    2.05
     %
    2.00
    %%
    1.72
     %%
    1.54
    %(
    1.52
     %(
    1.50
    %%%
    1.48
    %,
    1.47
     %,
    1.47
    %%%%
    1.45
    Activations Density 0.015%

    No Known Activations