© 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. 10-GEMMASCOPE-RES-131K
    7. 68720
    Prev
    Next
    INDEX
    Explanations

    decisions and actions

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

    The neuron peaks on base‐form action verbs following “to” (i.e. infinitive verbs).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    For
    -1.61
     D
    -1.57
     So
    -1.52
     L
    -1.48
     That
    -1.46
     EVERY
    -1.42
     F
    -1.40
     G
    -1.40
     O
    -1.39
     As
    -1.39
    POSITIVE LOGITS
     alcune
    1.52
     hırka
    1.49
     eşofman
    1.45
     別注
    1.45
     côtés
    1.41
    
    1.41
     teknologi
    1.40
     compétences
    1.39
     prochaines
    1.39
     pérd
    1.38
    Activations Density 0.062%

    No Known Activations