© 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. 104950
    Prev
    Next
    INDEX
    Explanations

    meta-prefix words

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

    The neuron primarily activates on occurrences of the substring “meta” within 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
    joyed
    -1.48
     who
    -1.32
    疑惑
    -1.31
    Արտաքին
    -1.27
    €™
    -1.26
     kiedy
    -1.20
     according
    -1.20
     from
    -1.20
    赑
    -1.16
     when
    -1.16
    POSITIVE LOGITS
     mutfak
    1.37
     procès
    1.32
     Aliens
    1.27
     keş
    1.25
    細かい
    1.22
     accessoire
    1.21
    也會
    1.20
    オシャレ
    1.20
    Kondisi
    1.19
     parfüm
    1.19
    Activations Density 0.073%

    No Known Activations