Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8310
    Prev
    Next
    INDEX
    Explanations

    male and female demographics

    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
     during
    -0.95
     没有
    -0.84
     when
    -0.84
     prevent
    -0.82
     ....
    -0.80
     one
    -0.79
     drugs
    -0.78
     .....
    -0.78
    čilo
    -0.78
     親
    -0.77
    POSITIVE LOGITS
     female
    2.89
     females
    2.80
     Female
    2.30
    female
    2.27
    Female
    2.06
     Females
    2.03
     women
    2.02
     male
    1.90
     ladies
    1.80
     girls
    1.77
    Activations Density 0.043%

    No Known Activations