© 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. 65688
    Prev
    Next
    INDEX
    Explanations

    gaining popularity or momentum

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

    The neuron fires on words and phrases that signal upward momentum or growing popularity (e.g. “popularity,” “gathering steam,” “gain traction,” “momentum,” 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
     there
    -1.88
    kript
    -1.55
    Usually
    -1.53
     much
    -1.52
    Often
    -1.50
     roughly
    -1.47
    If
    -1.46
    Without
    -1.41
     very
    -1.41
     only
    -1.41
    POSITIVE LOGITS
     and
    1.75
    ("")){
    1.52
    gencias
    1.46
    ﮧ
    1.43
    Ꮀ
    1.42
    AutoresizingMask
    1.42
     серпня
    1.42
    蚡
    1.41
    ticiones
    1.40
     from
    1.39
    Activations Density 0.033%

    No Known Activations