© 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. 107915
    Prev
    Next
    INDEX
    Explanations

    labor relations

    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
     hack
    -0.82
    ียด
    -0.79
    Interop
    -0.76
     hacked
    -0.74
    hack
    -0.74
     május
    -0.74
    ochial
    -0.73
     haunted
    -0.73
    wohnt
    -0.72
     IAEA
    -0.71
    POSITIVE LOGITS
     relations
    1.98
     Relations
    1.87
     relation
    1.54
     Relation
    1.42
    relations
    1.42
    Relations
    1.41
    关系
    1.33
     RELATIONS
    1.30
    Relation
    1.28
     relaciones
    1.28
    Activations Density 0.029%

    No Known Activations