© 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. 60755
    Prev
    Next
    INDEX
    Explanations

    daughter

    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
     boyhood
    -1.27
     boys
    -1.22
     vợ
    -1.14
     現在
    -1.13
     Erkennt
    -1.10
     brothers
    -1.04
     macho
    -1.01
    AR
    -1.01
     fracas
    -1.00
     αυτά
    -1.00
    POSITIVE LOGITS
    Daughter
    1.67
    daughter
    1.61
     Daughter
    1.60
     daughter
    1.44
    婿
    1.17
     daughters
    1.16
    aughters
    1.14
     who
    1.09
    daughters
    1.08
     caneta
    1.08
    Activations Density 0.005%

    No Known Activations