© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15233
    Prev
    Next
    INDEX
    Explanations

    first to be

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

    This neuron detects infinitive verb constructions, i.e. a “to” followed by a verb.

    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
     {
    
    
    -1.97
    )$.
    -1.80
    。"
    -1.58
     Reſ
    -1.57
    )、
    -1.57
    ),
    -1.55
     tragedia
    -1.55
    」。
    -1.52
    )$,
    -1.52
    )。
    -1.52
    POSITIVE LOGITS
     of
    2.06
     before
    1.90
     than
    1.79
     on
    1.76
     Of
    1.72
    のだが
    1.70
     prior
    1.65
     such
    1.63
    ,
    1.59
     after
    1.59
    Activations Density 0.020%

    No Known Activations