© 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. 34-GEMMASCOPE-RES-131K
    4. 117889
    Prev
    Next
    INDEX
    Explanations

    movement or travel

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

    The neuron flags high–information content words—primarily open-class nouns and verbs—rather than common function words.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     hitting
    -0.97
    into
    -0.84
     домой
    -0.79
     instala
    -0.79
    junta
    -0.78
    起
    -0.77
     into
    -0.77
    させ
    -0.76
     bleibt
    -0.76
     landings
    -0.76
    POSITIVE LOGITS
     travel
    2.27
     travelling
    1.85
     travels
    1.84
     traveled
    1.84
     traveling
    1.79
     travelled
    1.77
     journey
    1.71
    travel
    1.66
    Travel
    1.65
    Travelling
    1.55
    Activations Density 0.130%

    No Known Activations