© 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. 12134
    Prev
    Next
    INDEX
    Explanations

    Dior, Christian, Chiranjeevi, Cibyl

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

    The neuron fires on capitalized multi‐word names and titles—i.e. proper‐noun sequences like brand or club names.

    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
     turtle
    -0.82
    ި
    -0.81
    gac
    -0.79
    ゙
    -0.77
     axial
    -0.75
     cannon
    -0.72
     kunde
    -0.72
    ˩
    -0.72
    Everyday
    -0.72
     Parton
    -0.71
    POSITIVE LOGITS
     Dior
    1.23
    Dior
    1.02
     dior
    0.81
    ierz
    0.81
     oblique
    0.81
     superstitious
    0.78
    dior
    0.75
     SAU
    0.74
     toile
    0.74
    Christian
    0.74
    Activations Density 0.012%

    No Known Activations