© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93704
    Prev
    Next
    INDEX
    Explanations

    entity relation types

    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
    kinetic
    -0.79
     iemand
    -0.77
    Oacute
    -0.77
    活跃
    -0.75
     Sinaloa
    -0.74
     kuf
    -0.73
    Kah
    -0.72
     Merritt
    -0.71
     ترکیب
    -0.71
    Sain
    -0.70
    POSITIVE LOGITS
     relationship
    2.55
     relationships
    2.36
     relation
    2.11
     relations
    2.00
    relationship
    1.99
     Relationship
    1.83
     Relationships
    1.77
    Relationship
    1.73
     relación
    1.70
    Relation
    1.66
    Activations Density 0.097%

    No Known Activations