© 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. 75714
    Prev
    Next
    INDEX
    Explanations

    possessions and belongings

    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
    ργο
    -0.79
    že
    -0.74
     kraj
    -0.73
     Maat
    -0.73
     Geraadpleegd
    -0.72
    OPO
    -0.71
    cimentos
    -0.71
     én
    -0.70
    álen
    -0.70
    ctivité
    -0.69
    POSITIVE LOGITS
     belongings
    4.28
     possessions
    3.78
     items
    2.38
    belong
    2.34
     stuff
    2.34
     Belong
    2.20
     valuables
    2.11
     belonging
    2.08
     possession
    1.97
     things
    1.95
    Activations Density 0.043%

    No Known Activations