© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39148
    Prev
    Next
    INDEX
    Explanations

    above and below

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

    The neuron fires on call-to-action navigation instructions (e.g. “click the button below,” “see links below,” etc.).

    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
     générer
    -1.33
     使っ
    -1.32
     داشتم
    -1.27
    still
    -1.25
    āciju
    -1.24
     băr
    -1.18
    越来越
    -1.17
    ovací
    -1.16
     they
    -1.15
     acolo
    -1.15
    POSITIVE LOGITS
     for
    1.52
     to
    1.41
     of
    1.33
    ’
    1.27
     at
    1.22
     Кубка
    1.22
    t
    1.20
    washingtonpost
    1.19
     nicht
    1.17
     available
    1.16
    Activations Density 0.029%

    No Known Activations