© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59351
    Prev
    Next
    INDEX
    Explanations

    AB followed by common abbreviations

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

    The neuron specifically detects occurrences of the uppercase bigram "AB" in the text.

    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
    槩
    -2.84
    是大
    -2.58
    是非常
    -2.50
    ねえ
    -2.45
    時間も
    -2.31
    嫱
    -2.27
    not
    -2.27
    所以我
    -2.25
    some
    -2.23
     incomparable
    -2.20
    POSITIVE LOGITS
     ก็
    2.47
     forego
    2.27
     us
    2.25
     laajenta
    2.22
    拇
    2.19
     genius
    2.17
     этом
    2.16
    t
    2.13
    綿
    2.09
     Then
    2.03
    Activations Density 0.008%

    No Known Activations