© 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. 98608
    Prev
    Next
    INDEX
    Explanations

    siblings or brothers

    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
     Fournier
    -0.71
     Reproductive
    -0.71
    кування
    -0.70
    Ꭰ
    -0.67
     Twentieth
    -0.67
    Zal
    -0.67
    NX
    -0.65
    したのは
    -0.64
    Ito
    -0.63
    tische
    -0.63
    POSITIVE LOGITS
     siblings
    5.50
     sibling
    5.16
    siblings
    4.13
    sibling
    4.13
     Siblings
    3.86
    Sibling
    3.80
    Siblings
    3.64
     Sib
    3.53
     sib
    3.34
     brothers
    2.92
    Activations Density 0.082%

    No Known Activations