© 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. 22-GEMMASCOPE-RES-131K
    7. 72811
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and 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_22/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
     into
    -1.16
     known
    -1.00
     rallado
    -0.89
    ÉE
    -0.88
    ributor
    -0.88
    maxValue
    -0.88
     kuu
    -0.86
     followed
    -0.85
     overeen
    -0.82
    ogues
    -0.82
    POSITIVE LOGITS
     responsibility
    1.37
     own
    1.07
    MINE
    1.05
     prerogative
    1.01
    몫
    1.00
     respons
    1.00
    belong
    0.98
     initiative
    0.95
     responsab
    0.95
    を作り
    0.94
    Activations Density 0.022%

    No Known Activations