© 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. 10-GEMMASCOPE-RES-131K
    4. 101835
    Prev
    Next
    INDEX
    Explanations

    MA followed by varied tokens

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

    The neuron is a detector for the uppercase bigram “MA” (e.g. as a standalone abbreviation in 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
    榈
    -2.86
     мои
    -2.58
    /")
    -2.38
    劼
    -2.28
    las
    -2.23
    riculares
    -2.20
     weißem
    -2.20
     estekak
    -2.20
     verheir
    -2.20
    }};
    -2.14
    POSITIVE LOGITS
    9
    2.58
    uttori
    2.52
     nouvelles
    2.31
     be
    2.30
    1
    2.23
    쫀
    2.17
    4
    2.14
     he
    2.14
    久し
    2.13
     '';
    1.95
    Activations Density 0.004%

    No Known Activations