© 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. 6781
    Prev
    Next
    INDEX
    Explanations

    numerical measurements

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

    The neuron never fires—it does not detect any consistent pattern (i.e. it is effectively inactive or “dead”).

    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
    ０
    -1.05
    私が
    -0.96
    なぜ
    -0.87
    Οι
    -0.87
    人気
    -0.85
    यह
    -0.85
    皆様
    -0.84
    僕は
    -0.84
    最近は
    -0.83
    ティ
    -0.83
    POSITIVE LOGITS
     входа
    0.91
     piratas
    0.90
     calamity
    0.81
    寄生
    0.79
    褥
    0.79
    MNA
    0.78
    loha
    0.77
    茹
    0.77
    急速
    0.77
    Bek
    0.77
    Activations Density 0.037%

    No Known Activations