© 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. 47895
    Prev
    Next
    INDEX
    Explanations

    will be present

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

    The neuron spotlights future‐tense modal auxiliaries (e.g. “will,” “would”).

    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
     even
    -1.84
     be
    -1.65
     as
    -1.61
     for
    -1.48
     religieuses
    -1.44
     very
    -1.41
    もちゃ
    -1.41
    lapis
    -1.34
     právě
    -1.34
     monumentos
    -1.30
    POSITIVE LOGITS
    },{
    
    1.78
     probablement
    1.69
    es
    1.65
    
    1.57
    ns
    1.57
    most
    1.48
    probably
    1.46
    太多
    1.45
    ATION
    1.41
    cked
    1.41
    Activations Density 0.165%

    No Known Activations