© 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. 48133
    Prev
    Next
    INDEX
    Explanations

    family members and friends

    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
    ナイキ
    -1.10
    Probl
    -1.06
    CAPÍTULO
    -1.05
    CAPITULO
    -0.99
     otot
    -0.99
     efic
    -0.98
    INGRED
    -0.98
    可谓
    -0.96
    声優
    -0.96
    Informações
    -0.96
    POSITIVE LOGITS
     brother
    2.92
     daughter
    2.92
     sister
    2.83
     son
    2.77
     mother
    2.77
     father
    2.63
     husband
    2.63
     wife
    2.50
     dad
    2.05
     cousin
    2.03
    Activations Density 0.064%

    No Known Activations