© 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. 65596
    Prev
    Next
    INDEX
    Explanations

    song titles

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

    This neuron detects numbered list items—particularly track‐listing entries with their index numbers and song titles.

    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
    asics
    -0.97
     Gerente
    -0.95
     trợ
    -0.93
     möchtest
    -0.92
    alló
    -0.92
     Posteriormente
    -0.92
     supera
    -0.91
     Actualmente
    -0.91
     sítio
    -0.90
    женных
    -0.90
    POSITIVE LOGITS
    intro
    1.00
     Song
    0.96
     Pt
    0.91
    км
    0.91
     traditionnels
    0.90
     Intro
    0.89
     song
    0.88
    ol
    0.87
    Pt
    0.86
     Boulevard
    0.86
    Activations Density 0.068%

    No Known Activations