© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20918
    Prev
    Next
    INDEX
    Explanations

    words starting with Ab

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

    The neuron reliably fires on the two-letter sequence “Ab,” i.e. the prefix “Ab” as it appears at the start of names or 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_10/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
    鹮
    -3.44
    戋
    -2.94
    嵛
    -2.81
    犼
    -2.73
    」，
    -2.70
    
    -2.67
     aceites
    -2.64
    也将
    -2.63
    也会
    -2.55
    赑
    -2.52
    POSITIVE LOGITS
    7
    3.72
    3
    3.52
    2
    3.45
    0
    3.39
    9
    3.27
    1
    3.17
    *
    3.14
    --
    2.88
    4
    2.78
     &
    2.73
    Activations Density 0.007%

    No Known Activations