© 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. 92826
    Prev
    Next
    INDEX
    Explanations

    religious adherents and followers

    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
     prophets
    -1.02
    Customers
    -0.93
     prophet
    -0.85
    Prophet
    -0.85
     founders
    -0.83
    ⫺
    -0.82
    vater
    -0.78
    clubs
    -0.77
    Founder
    -0.76
     Prophet
    -0.75
    POSITIVE LOGITS
     disciples
    1.10
     disciple
    1.09
     student
    0.98
     devotee
    0.96
     devotees
    0.92
    rentice
    0.91
     faithful
    0.89
     believer
    0.86
     devoted
    0.85
    信
    0.85
    Activations Density 0.022%

    No Known Activations