© 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. 10-GEMMASCOPE-RES-131K
    7. 112921
    Prev
    Next
    INDEX
    Explanations

    the

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

    The neuron reliably activates on decimal numeric measurements (numbers with a fractional “.5” component).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蔟
    -2.13
    istani
    -2.00
     awakeFromNib
    -1.95
    ytale
    -1.93
     BRASIL
    -1.88
    靫
    -1.87
    ⛦
    -1.86
    
    -1.86
    pography
    -1.84
    ;';
    -1.81
    POSITIVE LOGITS
    _
    2.47
    {
    2.33
    *
    2.09
     одним
    1.96
    '
    1.91
     \
    1.89
     {
    1.85
     N
    1.82
     
    1.80
     K
    1.77
    Activations Density 0.091%

    No Known Activations