© 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. 20730
    Prev
    Next
    INDEX
    Explanations

    categories or groups

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

    The neuron mainly detects plural nouns (words ending in “-s”).

    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
     beserta
    -1.36
     sekä
    -1.34
    <bos>
    -1.26
     ваш
    -1.22
     anderer
    -1.18
    RODU
    -1.13
     you
    -1.11
    Deskripsi
    -1.10
     azonban
    -1.10
     rapidement
    -1.10
    POSITIVE LOGITS
     ones
    1.34
    を搭載
    1.29
     merely
    1.20
    を行いました
    1.20
    ggars
    1.19
     inroads
    1.16
     whose
    1.14
     litri
    1.13
     brukes
    1.12
    URIDAD
    1.12
    Activations Density 0.192%

    No Known Activations