© 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. 9158
    Prev
    Next
    INDEX
    Explanations

    Sai Baba, Amman, Ganes, Ganga

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

    The neuron reliably activates on the letter sequence “aji” (and close variants) as found in Indian proper names.

    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
    ’
    -1.70
    -
    -1.64
     був
    -1.48
    </i>
    -1.40
    ⠋
    -1.36
     colar
    -1.35
    ,"
    -1.34
     ήταν
    -1.33
     beetje
    -1.30
     décembre
    -1.29
    POSITIVE LOGITS
     lunghi
    1.48
     are
    1.45
     to
    1.45
    "]));
    1.42
     являются
    1.39
    InstrumentedTest
    1.38
     лишь
    1.38
    are
    1.36
     {
    1.34
     aspek
    1.34
    Activations Density 0.019%

    No Known Activations