© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62549
    Prev
    Next
    INDEX
    Explanations

    transitioning to new activities

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

    The neuron flags infinitive constructions—instances of “to” plus a verb (and related future‐oriented verb forms like “will”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     لیتر
    -1.19
    veux
    -0.95
     successo
    -0.88
    뿐
    -0.87
    IDENTIFIED
    -0.85
    still
    -0.85
     حتی
    -0.85
     GETTING
    -0.84
     foresee
    -0.84
    pue
    -0.83
    POSITIVE LOGITS
     pursue
    1.33
     begin
    1.32
     avoid
    1.27
     attend
    1.20
     await
    1.16
     aufgrund
    1.08
     join
    1.08
     prevent
    1.05
     embark
    1.02
     bergabung
    1.01
    Activations Density 0.040%

    No Known Activations