© 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. 22-GEMMASCOPE-RES-131K
    7. 71544
    Prev
    Next
    INDEX
    Explanations

    date and version numbers

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

    The neuron fires on programming‐identifier tokens (names of variables, attributes, fields, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     recognize
    -1.02
    idem
    -0.97
    の良い
    -0.97
    的同时
    -0.96
     حاول
    -0.96
     wiem
    -0.94
     declaração
    -0.92
     hielt
    -0.92
    رنگ
    -0.90
    /***
    -0.90
    POSITIVE LOGITS
    Ramen
    1.07
     postage
    0.91
    Parfait
    0.89
    ！");
    0.86
    なので
    0.82
    kanı
    0.81
    Това
    0.81
    Поэтому
    0.80
    Warmly
    0.79
     Хан
    0.79
    Activations Density 0.010%

    No Known Activations