© 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. 90703
    Prev
    Next
    INDEX
    Explanations

    stellar feedback and star formation

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

    The neuron is particularly tuned to pick out the key technical and domain‐specific terms (object names, acronyms, study concepts, and method keywords) in scientific paper abstracts.

    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
    angal
    -0.88
     δο
    -0.80
     ,.
    -0.74
    ças
    -0.73
     inertia
    -0.73
    eking
    -0.73
     ficar
    -0.72
    viny
    -0.70
     rest
    -0.69
    öl
    -0.69
    POSITIVE LOGITS
     methodological
    0.88
     vientos
    0.82
    Вопрос
    0.81
     winds
    0.81
     nurseries
    0.79
    坞
    0.78
     intermittent
    0.75
    artney
    0.73
    брита
    0.73
     concursos
    0.72
    Activations Density 0.044%

    No Known Activations