© 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. 34-GEMMASCOPE-RES-131K
    7. 76944
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

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

    The neuron detects promise‐style “.then” calls (i.e. occurrences of the keyword then in promise chains).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    注明
    -0.95
    ないけど
    -0.93
     desapar
    -0.91
    ameran
    -0.91
    Eme
    -0.88
    でもいい
    -0.88
    Riverside
    -0.88
    Коммента
    -0.87
    zetten
    -0.86
     bequem
    -0.86
    POSITIVE LOGITS
    ok
    0.97
    Let
    0.94
    }$.
    0.94
    Why
    0.93
    tham
    0.90
    when
    0.89
    リ
    0.89
    褰
    0.89
    0.89
    ().
    0.88
    Activations Density 0.002%
    No Known Activations