© 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. 10-GEMMASCOPE-RES-131K
    7. 12842
    Prev
    Next
    INDEX
    Explanations

    having or possessing something

    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
    -
    -2.36
     itself
    -1.70
    ."
    -1.70
     pourrait
    -1.67
     laquelle
    -1.63
    ates
    -1.52
    </u>
    -1.52
     was
    -1.49
     egna
    -1.48
     today
    -1.42
    POSITIVE LOGITS
     to
    2.16
     who
    1.90
    AdvEx
    1.76
    ⚋
    1.73
    鵟
    1.66
    zembro
    1.60
    ℟
    1.57
    
    1.55
     transferir
    1.55
    tdessen
    1.55
    Activations Density 0.105%

    No Known Activations