© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165267
    Prev
    Next
    INDEX
    Explanations

    interconnected neurons and nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     governing
    0.42
    ">=</
    0.41
     consolidated
    0.41
    指导
    0.41
     decoded
    0.40
     حکومت
    0.40
     Consolidated
    0.39
     ውጤ
    0.39
    왕
    0.39
     codified
    0.38
    POSITIVE LOGITS
     neurons
    0.95
    Neurons
    0.91
     neuron
    0.84
    neurons
    0.83
     nodes
    0.79
     node
    0.77
     Neur
    0.72
     Neuron
    0.70
    nodes
    0.68
    Nodes
    0.68
    Activations Density 0.037%

    No Known Activations