© 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. 90772
    Prev
    Next
    INDEX
    Explanations

    software, 1, Guitar, Vee, Characterization

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

    The neuron fires on programming‐style namespace qualifiers and separators (e.g. “global”, “::”, “.”).

    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
     at
    -0.93
    家は
    -0.89
     by
    -0.88
     as
    -0.84
     during
    -0.83
    찔
    -0.81
     bringing
    -0.81
    閏
    -0.78
    zyści
    -0.77
     turned
    -0.77
    POSITIVE LOGITS
    ぱ
    0.93
     konkret
    0.86
     ぱ
    0.86
    inally
    0.85
    oner
    0.82
     albicans
    0.79
     ジ
    0.78
    🇧
    0.78
     anges
    0.78
     ™
    0.77
    Activations Density 0.000%

    No Known Activations