© 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. 73819
    Prev
    Next
    INDEX
    Explanations

    event types and situations

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

    The neuron responds to noun forms of actions or processes (nominalized verbs like “motion,” “confrontation,” “retreat,” “pursuit,” “position,” 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_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
     каком
    -0.80
     fallecimiento
    -0.79
    *}{
    -0.78
     хорошем
    -0.78
    扌
    -0.77
     mêmes
    -0.77
     одном
    -0.74
    きり
    -0.74
     dvě
    -0.73
    телите
    -0.73
    POSITIVE LOGITS
     type
    1.37
    式
    1.29
     mode
    1.19
     killings
    1.17
     marriages
    1.15
     式
    1.05
     style
    1.04
     pregnancies
    1.00
     version
    0.99
    模式
    0.99
    Activations Density 0.241%

    No Known Activations