© 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. 34-GEMMASCOPE-RES-131K
    7. 6703
    Prev
    Next
    INDEX
    Explanations

    blues music

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     sequelize
    -0.88
     orchestral
    -0.86
     archery
    -0.83
     Tapia
    -0.82
    ffmpeg
    -0.82
    ADP
    -0.80
    metingen
    -0.77
    鐢
    -0.77
    Orche
    -0.77
    DQ
    -0.77
    POSITIVE LOGITS
     blues
    2.52
     Blues
    2.34
    Blues
    2.19
    blues
    2.05
     Mississippi
    1.20
     блю
    1.15
    ブル
    1.08
    蓝
    1.07
     Alligator
    0.98
    Mississippi
    0.97
    Activations Density 0.052%

    No Known Activations