© 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. 22-GEMMASCOPE-RES-131K
    7. 66806
    Prev
    Next
    INDEX
    Explanations

    ring

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

    The neuron activates whenever the token “ring” (in any casing or as part of a title) appears in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    0
    -2.89
    $
    -2.64
    5
    -2.52
    椟
    -2.47
    苼
    -2.34
    臯
    -2.30
     geladeira
    -2.27
     banho
    -2.27
    4
    -2.22
    dersfield
    -2.20
    POSITIVE LOGITS
     Then
    2.31
     newcomer
    2.28
     pasas
    2.22
    🤜
    2.22
     realizando
    2.20
    кой
    2.19
     The
    2.16
    ENDENT
    2.11
    ！」
    2.08
     getNombre
    2.08
    Activations Density 0.009%

    No Known Activations