© 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. 38039
    Prev
    Next
    INDEX
    Explanations

    first past the post

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

    This neuron fires on the parenthetical metadata and list‐item tokens (years, parentheses, uppercase entry titles) that appear in disambiguation‐style lists.

    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
     razones
    -0.87
    Belum
    -0.85
    Manufact
    -0.82
     zugänglich
    -0.82
    Assignable
    -0.82
    IMDb
    -0.81
     fet
    -0.81
     로
    -0.81
     barata
    -0.80
     sut
    -0.79
    POSITIVE LOGITS
     "
    1.66
     “
    1.62
     '
    1.41
     ‘
    1.37
     Eat
    1.32
     eat
    1.27
     Buy
    1.12
     „
    1.09
     buy
    1.09
     Adopt
    1.09
    Activations Density 0.149%

    No Known Activations