© 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. 60168
    Prev
    Next
    INDEX
    Explanations

    boy and boys

    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
     women
    -1.14
     female
    -1.11
     people
    -1.05
     buque
    -1.05
    female
    -0.97
     Mühle
    -0.97
     watu
    -0.95
     rises
    -0.93
    到的
    -0.93
    ・・・。
    -0.93
    POSITIVE LOGITS
    Boys
    1.53
    👦
    1.51
    boys
    1.48
     boys
    1.46
     scouts
    1.43
     boy
    1.41
    boy
    1.41
     Boys
    1.34
     BOY
    1.33
    BOYS
    1.30
    Activations Density 0.009%

    No Known Activations