© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128024
    Prev
    Next
    INDEX
    Explanations

    .getElementById and object property access

    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
    ubro
    -0.98
    nologi
    -0.88
    película
    -0.86
     earlier
    -0.84
    вес
    -0.84
    ḩ
    -0.84
    sider
    -0.84
    sling
    -0.82
    पाल
    -0.82
     bibit
    -0.81
    POSITIVE LOGITS
     daugiau
    0.97
    gusting
    0.94
     juos
    0.86
     pasirink
    0.85
     Bof
    0.85
     apsau
    0.82
     Engel
    0.81
     экрана
    0.81
     Opin
    0.81
     }).
    0.80
    Activations Density 0.002%

    No Known Activations