© 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. 22-GEMMASCOPE-RES-131K
    7. 39412
    Prev
    Next
    INDEX
    Explanations

    his + noun describing person/thing

    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
     våra
    -1.09
     بیشتری
    -1.06
     campeón
    -1.02
    了什么
    -1.02
     jeder
    -1.02
    Commentaires
    -1.01
     possib
    -1.00
    มากกว่า
    -1.00
     pappa
    -0.98
    zegovina
    -0.97
    POSITIVE LOGITS
     fellow
    1.30
     a
    1.15
     colleagues
    1.13
    ometries
    1.13
     wife
    1.13
     another
    1.12
     own
    1.11
     dieną
    1.10
     that
    1.10
    ַּ
    1.05
    Activations Density 0.031%

    No Known Activations