© 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. 10-GEMMASCOPE-RES-131K
    7. 111284
    Prev
    Next
    INDEX
    Explanations

    figure references

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

    This neuron detects references to figures (e.g. “Fig. 1,” “Fig 392,” etc.) in the document.

    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
    ↵
    -3.64
    ࿚
    -2.61
    )’
    -2.52
     psychotic
    -2.52
    轫
    -2.48
     奶茶
    -2.47
    辚
    -2.45
    由此
    -2.44
    媗
    -2.42
    -“
    -2.41
    POSITIVE LOGITS
     {
    2.86
    y
    2.81
     '
    2.72
    
    2.61
    茳
    2.55
    Of
    2.52
     ของ
    2.48
    2
    2.45
    鉿
    2.38
    ic
    2.36
    Activations Density 0.005%

    No Known Activations