© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 677
    Prev
    Next
    INDEX
    Explanations

    powers and history

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

    The neuron activates on most substantive content words in running prose (e.g. narrative paragraphs) as opposed to headings, lists, or other markup.

    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
     akade
    -0.95
     rö
    -0.93
    Matem
    -0.91
     homicide
    -0.91
     ekonomi
    -0.90
    Obra
    -0.90
    Gost
    -0.90
    Boa
    -0.90
     :)
    -0.88
    Massa
    -0.88
    POSITIVE LOGITS
     energy
    1.22
    energy
    1.16
     even
    1.12
     powers
    1.03
     causes
    1.01
     Energy
    0.97
     transform
    0.97
     powered
    0.96
    zungs
    0.95
     causing
    0.94
    Activations Density 0.013%

    No Known Activations