© 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. 105149
    Prev
    Next
    INDEX
    Explanations

    named entities and their context

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

    The neuron predominantly activates on capitalized proper nouns—names of people, places, organizations, languages, 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_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
    akterysty
    -2.70
     немного
    -2.69
    。　　
    -2.59
    ،
    -2.55
     pensamientos
    -2.53
    埽
    -2.44
    。『
    -2.42
    他没有
    -2.38
     लेकिन
    -2.36
    峋
    -2.36
    POSITIVE LOGITS
    e
    3.98
    t
    3.20
    an
    3.17
    y
    3.00
    0
    2.91
    ic
    2.88
    as
    2.84
    c
    2.78
    b
    2.70
    to
    2.69
    Activations Density 0.004%

    No Known Activations