© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82290
    Prev
    Next
    INDEX
    Explanations

    children's hospitals

    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
     Elderly
    -0.90
     cocaína
    -0.78
     elderly
    -0.75
     pronunci
    -0.72
     fır
    -0.70
    Bred
    -0.69
    گار
    -0.68
     men
    -0.67
     children
    -0.67
     metabolismo
    -0.66
    POSITIVE LOGITS
    aksanaan
    0.94
     szpital
    0.84
     UPM
    0.84
    беріга
    0.83
     DCM
    0.79
     assent
    0.79
    ྫ
    0.77
    ASTER
    0.77
    AVAN
    0.76
     hospital
    0.76
    Activations Density 0.052%

    No Known Activations