© 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. 75895
    Prev
    Next
    INDEX
    Explanations

    German words ending in -ild, -old

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

    The neuron is strongly activated by capitalized tokens that are part of named entities (proper nouns).

    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
    etzung
    -0.80
     Prudence
    -0.73
     Rasmus
    -0.73
    Ciudad
    -0.72
    どうなる
    -0.72
    実践
    -0.69
    كد
    -0.69
     beitragen
    -0.69
     Conventional
    -0.68
     QD
    -0.68
    POSITIVE LOGITS
    romeda
    0.92
     fashioned
    0.87
     harmless
    0.82
    更好的
    0.80
     artesanato
    0.80
     ciep
    0.78
     europeos
    0.77
    //
    0.76
    fiers
    0.76
     suel
    0.75
    Activations Density 0.042%

    No Known Activations