© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91372
    Prev
    Next
    INDEX
    Explanations

    handling errors or exceptions

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

    This neuron fires on isolated numeric tokens and uppercase/abbreviated codes (e.g. “936,” “PANIC,” “AP,” “5,” “616”).

    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
     المركز
    -0.77
    zone
    -0.73
    yml
    -0.68
     rộng
    -0.66
     HV
    -0.66
    RZ
    -0.66
     Vay
    -0.65
    texts
    -0.63
    NGS
    -0.63
    samp
    -0.62
    POSITIVE LOGITS
    カプ
    0.77
    COM
    0.71
    메
    0.68
     設計
    0.66
     Klang
    0.66
    ühle
    0.66
    Портал
    0.64
    jera
    0.63
     painless
    0.63
    tites
    0.63
    Activations Density 0.076%

    No Known Activations