© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26992
    Prev
    Next
    INDEX
    Explanations

    marriage relationship discussions

    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_22/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
     in
    -1.00
    })*/
    -0.97
    
    -0.96
     protections
    -0.93
     people
    -0.93
     to
    -0.92
     توم
    -0.92
    ors
    -0.89
    🎓
    -0.88
    -0.88
    POSITIVE LOGITS
    veto
    1.09
    curricular
    1.05
    ladı
    1.01
    平时
    1.01
     spouse
    1.01
     family
    0.98
     Accesorios
    0.97
     tropicales
    0.96
     význam
    0.95
     hjemme
    0.95
    Activations Density 0.064%

    No Known Activations