© 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. 58971
    Prev
    Next
    INDEX
    Explanations

    young people or individuals

    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
    増加
    -0.95
    adins
    -0.91
    zczegól
    -0.90
    Максим
    -0.90
     suckers
    -0.90
    ölk
    -0.89
     noastre
    -0.85
    locene
    -0.84
    Жизнь
    -0.84
     Apprenticeship
    -0.83
    POSITIVE LOGITS
     woman
    5.03
     girl
    4.31
     lady
    3.97
     guy
    3.14
     young
    3.02
     female
    2.98
    woman
    2.91
     women
    2.89
     gentleman
    2.84
     boy
    2.70
    Activations Density 0.169%

    No Known Activations