© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 23959
    Prev
    Next
    INDEX
    Explanations

    Follow this or follow up

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

    The neuron activates on the word “Follow” when it appears as a call-to-action (e.g. “Follow this and additional works at…”).

    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
     be
    -3.02
    "
    -2.95
    ’
    -2.92
    '
    -2.80
    {
    -2.64
     was
    -2.63
     has
    -2.56
    </h1>
    -2.50
     podemos
    -2.48
     u
    -2.47
    POSITIVE LOGITS
    ⛦
    3.45
    谂
    3.22
    咘
    3.03
    ☫
    3.00
    媖
    2.97
     był
    2.97
    ꯶
    2.91
     multitude
    2.83
     皇族
    2.66
    ꯸
    2.66
    Activations Density 0.070%

    No Known Activations