© 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. 40742
    Prev
    Next
    INDEX
    Explanations

    Abelian or Abe

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

    The neuron fires on occurrences of the character sequence “Abe,” detecting that exact substring in 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
    ar
    -2.83
    ⑊
    -2.72
    蓠
    -2.67
    那我
    -2.64
     этими
    -2.63
    噌
    -2.63
    る
    -2.56
    是他
    -2.52
    ㍑
    -2.50
    并没有
    -2.47
    POSITIVE LOGITS
     It
    3.11
    ⦊
    3.08
     If
    2.98
    ↵
    2.50
    *
    2.27
     When
    2.20
     вслед
    2.19
    eadilan
    2.13
    F
    2.03
    猡
    2.03
    Activations Density 0.003%

    No Known Activations