© 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. 93097
    Prev
    Next
    INDEX
    Explanations

    Christians and believers

    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
    iska
    -0.91
    gebra
    -0.91
    quela
    -0.86
    APL
    -0.85
    Operators
    -0.82
    相手
    -0.81
     appellants
    -0.81
     Guys
    -0.81
     Operators
    -0.81
     fixes
    -0.80
    POSITIVE LOGITS
     Christians
    2.66
     believers
    2.27
     followers
    2.27
     Christian
    2.23
    Christians
    2.06
    Christian
    1.81
     believer
    1.79
     follower
    1.76
    followers
    1.64
     faithful
    1.63
    Activations Density 0.027%

    No Known Activations