© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71415
    Prev
    Next
    INDEX
    Explanations

    possession or ownership

    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_10/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
     they
    -1.53
     there
    -1.52
     ansi
    -1.39
     conector
    -1.27
     UILabel
    -1.27
    ztés
    -1.26
     the
    -1.19
     in
    -1.16
    NEYS
    -1.13
     שם
    -1.11
    POSITIVE LOGITS
    ();
    1.56
     drenaje
    1.56
     absorción
    1.56
     conglomerate
    1.52
     caído
    1.51
    一个
    1.47
     levantó
    1.45
    很不
    1.44
     respondió
    1.43
     estímulo
    1.43
    Activations Density 0.035%

    No Known Activations