© 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. 92738
    Prev
    Next
    INDEX
    Explanations

    Christian suffering and regeneration

    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
     wyn
    -0.73
     comuniques
    -0.69
     biệt
    -0.69
     Recruitment
    -0.68
    槲
    -0.67
     пра
    -0.67
     நீ
    -0.66
    glBindTexture
    -0.66
     Feedback
    -0.65
     نوشته
    -0.65
    POSITIVE LOGITS
     sons
    0.98
     groans
    0.97
     groaning
    0.95
    Ʀ
    0.94
     groan
    0.91
    Spirit
    0.90
     Sons
    0.87
     adoption
    0.84
    āciju
    0.82
    ⤴
    0.79
    Activations Density 0.008%

    No Known Activations