© 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. 2443
    Prev
    Next
    INDEX
    Explanations

    individuals or people

    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
    สมบัติ
    -0.90
     tuturor
    -0.88
     archiv
    -0.83
    
    -0.82
    }}/>
    -0.81
    稔
    -0.81
    你们
    -0.79
     Erst
    -0.79
    niers
    -0.79
     hemma
    -0.78
    POSITIVE LOGITS
     individuals
    5.28
    Individuals
    4.00
     Individuals
    3.81
    individuals
    3.73
     person
    3.27
     people
    2.95
     persons
    2.84
     افراد
    2.81
     individuos
    2.75
     человека
    2.59
    Activations Density 0.251%

    No Known Activations