© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    Romance or Romeo

    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
    presto
    -0.79
    Banda
    -0.77
    ेंट
    -0.74
    WANT
    -0.74
    รัฐ
    -0.73
    äne
    -0.73
     Pati
    -0.73
    裘
    -0.70
    橡胶
    -0.70
    Occurrences
    -0.69
    POSITIVE LOGITS
     completos
    0.79
     ته
    0.76
    wdriver
    0.76
     Blazer
    0.75
     κάνει
    0.74
     pericolo
    0.74
    结
    0.74
    기도
    0.73
    夫婦
    0.73
     弾
    0.70
    Activations Density 0.010%

    No Known Activations