© 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. 78518
    Prev
    Next
    INDEX
    Explanations

    ancestors and hierarchy traversal

    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
    parcel
    -0.76
     imagina
    -0.75
    başı
    -0.73
    妃
    -0.70
    перед
    -0.69
     remaining
    -0.69
    enderal
    -0.69
    Paired
    -0.68
    underscore
    -0.67
     cheval
    -0.66
    POSITIVE LOGITS
     ancestors
    2.28
     ancestor
    2.05
     ancestry
    1.78
    祖
    1.58
     grandparents
    1.53
    cestors
    1.45
    Ancestor
    1.44
    ancestor
    1.43
     ancest
    1.40
     chain
    1.35
    Activations Density 0.053%

    No Known Activations