© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108542
    Prev
    Next
    INDEX
    Explanations

    young age

    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
    ītā
    -0.80
     Tomé
    -0.78
    漫畫
    -0.78
     gange
    -0.73
    íma
    -0.73
    ביוגרפיה
    -0.73
    шень
    -0.71
     gece
    -0.71
     Biotechnology
    -0.71
     luis
    -0.70
    POSITIVE LOGITS
     young
    5.44
    young
    4.00
     YOUNG
    3.38
    Young
    3.20
     Young
    3.14
     jeune
    3.03
     younger
    2.86
    YOUNG
    2.83
     jungen
    2.78
     jeunes
    2.77
    Activations Density 0.069%

    No Known Activations