© 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. 75508
    Prev
    Next
    INDEX
    Explanations

    female partners and mothers

    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
     ${({
    -1.09
     strade
    -0.95
    彼女
    -0.95
     brotherhood
    -0.94
    给她
    -0.93
    Rechts
    -0.93
     вона
    -0.90
    把她
    -0.90
    ˥
    -0.90
     nato
    -0.87
    POSITIVE LOGITS
     his
    1.25
     nag
    1.25
     pregnant
    1.11
     nagging
    1.09
     he
    1.09
    pregnant
    1.08
     ihm
    1.03
     herself
    1.02
     supportive
    1.00
     pregnancy
    0.96
    Activations Density 0.040%

    No Known Activations