© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69897
    Prev
    Next
    INDEX
    Explanations

    great-nieces, great-nephews, grandchildren

    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
    父亲
    -1.20
     отец
    -1.13
     parents
    -1.08
    Parents
    -1.08
    Dad
    -1.07
     Parents
    -1.07
     родителей
    -1.07
    父母
    -1.07
    Parent
    -1.06
    父親
    -1.03
    POSITIVE LOGITS
     nephew
    4.84
     niece
    4.66
     nieces
    4.56
     nephews
    4.44
     cousins
    3.08
     cousin
    3.02
     uncle
    2.70
     aunt
    2.25
     Nep
    2.20
    甥
    2.20
    Activations Density 0.026%

    No Known Activations