© 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. 107407
    Prev
    Next
    INDEX
    Explanations

    parent and Disney films

    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
     کشت
    -0.79
    dyr
    -0.77
    heit
    -0.69
     생성
    -0.68
     twar
    -0.66
    borough
    -0.66
    揾
    -0.66
    Correspond
    -0.66
    masa
    -0.65
     écran
    -0.65
    POSITIVE LOGITS
     Disney
    1.00
    Disney
    0.88
     εκεί
    0.79
     Parent
    0.78
     parental
    0.77
    disney
    0.77
     parent
    0.75
     Mortuary
    0.74
     fre
    0.74
     vía
    0.73
    Activations Density 0.029%

    No Known Activations