© 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. 56020
    Prev
    Next
    INDEX
    Explanations

    Electrical net zero

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

    The neuron activates on longer, domain-specific technical terms (such as “Electrical,” “Computer,” “primitive,” “clock,” etc.) often found in academic or code contexts.

    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
     Ahmad
    -0.81
     lika
    -0.75
    多种
    -0.74
    Ahmad
    -0.72
    Dean
    -0.72
     Dean
    -0.71
    WriteHeader
    -0.69
    StateManager
    -0.68
    EntryPoint
    -0.67
     BP
    -0.67
    POSITIVE LOGITS
    slides
    0.86
    oderma
    0.70
    спубли
    0.69
     Vlas
    0.68
     ngồi
    0.68
     Monate
    0.65
     tranh
    0.65
     WALTZ
    0.65
     porridge
    0.65
     Przy
    0.64
    Activations Density 0.122%

    No Known Activations