© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40237
    Prev
    Next
    INDEX
    Explanations

    young people's interests and conditions

    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
     virš
    -1.02
     женщина
    -0.97
    ลา
    -0.95
    failed
    -0.94
     jį
    -0.93
    preneurs
    -0.91
     asmen
    -0.91
     vandens
    -0.90
     mariage
    -0.89
     लोगों
    -0.89
    POSITIVE LOGITS
     young
    2.14
     kids
    1.75
     children
    1.70
     youth
    1.69
     child
    1.67
     kid
    1.63
     junior
    1.59
     youngster
    1.44
     teenager
    1.37
     parents
    1.36
    Activations Density 0.216%

    No Known Activations