© 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. 89811
    Prev
    Next
    INDEX
    Explanations

    how things work

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

    The neuron strongly activates on occurrences of the word “how,” especially in question or explanatory contexts.

    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
     discussione
    -0.79
     Handling
    -0.77
     đáp
    -0.75
     spectateurs
    -0.75
    Derbyniad
    -0.75
    solu
    -0.73
     solução
    -0.73
    ámetro
    -0.73
    CHUNK
    -0.73
     moyens
    -0.73
    POSITIVE LOGITS
     works
    2.83
     operates
    2.16
     работает
    1.95
     operate
    1.95
     funciona
    1.80
     Works
    1.79
     workings
    1.77
    works
    1.70
     работают
    1.66
     працю
    1.64
    Activations Density 0.102%

    No Known Activations