© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48533
    Prev
    Next
    INDEX
    Explanations

    princess, barbie, girl, dress

    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
     PARA
    -0.89
    ־
    -0.86
    Odkazy
    -0.85
    diem
    -0.84
     revised
    -0.81
     sandwiches
    -0.80
    浓郁
    -0.79
    Revised
    -0.79
     Copeland
    -0.79
     Revised
    -0.76
    POSITIVE LOGITS
     makeover
    1.13
     dress
    1.13
    мания
    0.95
     girl
    0.93
    זיה
    0.90
     girls
    0.85
     dziew
    0.84
     Condem
    0.83
     stupendous
    0.83
    ệu
    0.82
    Activations Density 0.019%

    No Known Activations