© 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. 128748
    Prev
    Next
    INDEX
    Explanations

    following and tracking

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

    The neuron activates on words denoting the act of following or tracking (e.g. follow, followed, following, tracking).

    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
    {
    -2.13
    Knowing
    -2.13
    Here
    -2.03
    Other
    -1.96
    According
    -1.91
    Aside
    -1.89
    笃
    -1.88
     se
    -1.80
    .’
    -1.80
    In
    -1.75
    POSITIVE LOGITS
    咈
    2.44
    ⛦
    2.30
    髎
    2.13
    莇
    2.11
     intently
    2.11
    棐
    2.08
    狁
    2.02
    我们
    2.02
    ครื่อง
    2.00
    ☫
    1.98
    Activations Density 0.099%

    No Known Activations