© 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. 10-GEMMASCOPE-RES-131K
    7. 104791
    Prev
    Next
    INDEX
    Explanations

    spatial relationships between entities

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

    The neuron activates on specialized scientific and technical terms (e.g. domain‐specific jargon) found in research 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_10/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
     complètement
    -1.62
    踮
    -1.48
     fortemente
    -1.40
     imó
    -1.35
     miſ
    -1.34
    IQUE
    -1.34
     quintessential
    -1.34
     solch
    -1.34
     собственности
    -1.33
     sturdy
    -1.32
    POSITIVE LOGITS
     with
    1.73
     during
    1.65
    bcryptjs
    1.61
     otro
    1.55
     at
    1.51
     through
    1.51
     before
    1.49
     in
    1.48
     Often
    1.46
     may
    1.41
    Activations Density 0.405%

    No Known Activations