© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31428
    Prev
    Next
    INDEX
    Explanations

    population counts and demographics

    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
    hamad
    -0.95
    AlreadyExists
    -0.91
     compensation
    -0.89
    ಞ
    -0.88
    setBold
    -0.87
    舩
    -0.84
     slår
    -0.84
    pado
    -0.83
    ENOS
    -0.83
    ATHERINE
    -0.82
    POSITIVE LOGITS
    Componentes
    0.90
     ремон
    0.90
    entist
    0.81
     gobern
    0.79
     Revised
    0.78
    ofollow
    0.76
    vs
    0.75
     disponib
    0.74
     whereas
    0.73
    nine
    0.73
    Activations Density 0.009%

    No Known Activations