© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    vault and vaulted ceilings

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

    The neuron activates on occurrences of the word “vault” (and its variants like “vaulted”) 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_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
     dezelve
    -3.11
     ſch
    -2.84
    ₶
    -2.83
    饜
    -2.81
    缡
    -2.73
    仉
    -2.72
    
    -2.64
    蔸
    -2.64
     juſ
    -2.59
    颼
    -2.55
    POSITIVE LOGITS
     
    3.55
    <bos>
    3.16
    ing
    2.70
    :
    2.53
     holen
    2.50
    As
    2.44
    to
    2.41
    要
    2.36
    ु
    2.33
    生まれ
    2.31
    Activations Density 0.002%

    No Known Activations