© 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. 70926
    Prev
    Next
    INDEX
    Explanations

    place, location, or context

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

    The neuron activates specifically on occurrences of the word “place.”

    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
    鹟
    -3.25
     gekocht
    -2.72
    妧
    -2.66
    錞
    -2.64
    粁
    -2.58
    絰
    -2.55
    事が
    -2.50
     Gedanke
    -2.45
    咿
    -2.45
     Шаг
    -2.44
    POSITIVE LOGITS
     oder
    3.08
     или
    2.75
    2.48
    或
    2.44
     atau
    2.44
     sia
    2.42
    También
    2.42
     поскольку
    2.41
    </em>
    2.34
     leur
    2.28
    Activations Density 0.037%

    No Known Activations