© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103383
    Prev
    Next
    INDEX
    Explanations

    names and organizations

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

    The neuron specializes in spotting capitalized proper nouns (e.g. names of people, shows, channels, 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
    anız
    -1.34
    quête
    -1.29
     here
    -1.28
     your
    -1.27
    おわりに
    -1.27
     čia
    -1.23
    ANIEL
    -1.17
     zima
    -1.17
     hotelu
    -1.17
     você
    -1.14
    POSITIVE LOGITS
    もいい
    1.45
     it
    1.39
    も良い
    1.29
    してました
    1.28
    StreetMap
    1.24
    を行います
    1.24
    を知る
    1.23
     úteis
    1.23
    来ました
    1.20
    Its
    1.19
    Activations Density 0.116%

    No Known Activations