© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107561
    Prev
    Next
    INDEX
    Explanations

    arches and vaults

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

    The neuron fires strongly on architectural structural and decorative terms—especially words naming elements like arches, vaults, dentils, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Dob
    -0.79
     border
    -0.77
    AppConfig
    -0.76
     Phosp
    -0.74
    补贴
    -0.73
    ohu
    -0.73
     Adonis
    -0.71
    idavit
    -0.71
    indakan
    -0.70
     Fury
    -0.69
    POSITIVE LOGITS
     vault
    1.40
     vaults
    1.35
     arches
    1.31
     Arches
    1.17
     arch
    1.16
    SUPPORTED
    1.14
     springing
    1.14
     unsupported
    1.13
     vaulted
    1.12
    拱
    1.05
    Activations Density 0.015%

    No Known Activations