© 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. 59728
    Prev
    Next
    INDEX
    Explanations

    owner or tenant occupation

    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
    sentence
    -0.91
     hermanas
    -0.86
     Visiting
    -0.85
    婚
    -0.85
    reichen
    -0.82
     Anbieter
    -0.81
    และ
    -0.81
     owner
    -0.81
    kesha
    -0.80
    gamb
    -0.79
    POSITIVE LOGITS
     ocupado
    1.17
     occupying
    1.17
     Occupied
    1.15
     occupied
    1.13
     occupy
    1.11
    occupied
    1.10
     OCCUP
    1.06
     occupies
    0.96
     Occup
    0.96
     occup
    0.88
    Activations Density 0.017%

    No Known Activations