© 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. 91651
    Prev
    Next
    INDEX
    Explanations

    of mine, yours, ours

    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
    至于
    -0.88
    といった
    -0.88
    ло
    -0.77
    ürger
    -0.76
    娲
    -0.75
     esos
    -0.75
    ichel
    -0.75
    лання
    -0.75
     कोई
    -0.74
    evsky
    -0.74
    POSITIVE LOGITS
     ours
    7.38
     mine
    7.34
     yours
    6.59
     theirs
    5.72
    Mine
    5.50
    mine
    5.47
     hers
    5.47
     Mine
    4.78
     Ours
    4.59
    Ours
    4.59
    Activations Density 0.341%

    No Known Activations