© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1430
    Prev
    Next
    INDEX
    Explanations

    possession, ownership, custody

    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
     lernen
    -0.75
    ard
    -0.73
    trc
    -0.72
    стройка
    -0.67
    ordinaire
    -0.67
    vespa
    -0.67
     ngừng
    -0.66
    Include
    -0.66
     maquillaje
    -0.65
     distinctions
    -0.65
    POSITIVE LOGITS
     possession
    5.41
     custody
    4.19
    possession
    3.97
     Possession
    3.47
     ownership
    2.83
     Custody
    2.58
     posesión
    2.47
    Poss
    2.39
     posses
    2.25
    cust
    2.19
    Activations Density 0.043%

    No Known Activations