© 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. 34-GEMMASCOPE-RES-131K
    7. 30560
    Prev
    Next
    INDEX
    Explanations

    represented representations

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

    This neuron detects opening punctuation tokens (like “(” or “<”) that introduce code constructs such as casts, function‐call parentheses, or generic/angle‐bracket type parameters.

    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
    萨
    -1.00
     where
    -0.93
    什么事
    -0.87
     luxo
    -0.84
     when
    -0.83
     would
    -0.82
     azule
    -0.82
    比べると
    -0.82
    贅沢
    -0.81
    씠
    -0.81
    POSITIVE LOGITS
    看到了
    1.05
    dalla
    0.92
     nossa
    0.92
     этого
    0.88
     нашим
    0.88
    Such
    0.87
    Our
    0.87
     такого
    0.87
    Ours
    0.86
    这样的
    0.86
    Activations Density 0.003%

    No Known Activations