© 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. 90656
    Prev
    Next
    INDEX
    Explanations

    synthesizing, continuously, moderately, modern

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

    The neuron fires strongly on the initial subword (first 5–6 letters) of longer, multi-syllable content words.

    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
     
    -4.59
     kleinen
    -2.52
     dilemma
    -2.44
     più
    -2.34
     In
    -2.28
     إل
    -2.28
    手下
    -2.27
    因为他
    -2.22
     hindrance
    -2.19
    難しい
    -2.14
    POSITIVE LOGITS
    寕
    3.81
    咴
    3.73
    厖
    3.33
    镦
    3.27
     uſed
    3.17
     wunderbar
    3.16
    遹
    3.05
    泐
    3.03
    
    3.03
     時尚
    3.03
    Activations Density 0.036%

    No Known Activations