© 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. 22-GEMMASCOPE-RES-131K
    7. 35434
    Prev
    Next
    INDEX
    Explanations

    email address and contact information

    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
     terá
    -1.01
    KPI
    -1.00
     gigantes
    -1.00
     peuvent
    -1.00
    межу
    -0.98
     anunció
    -0.98
    GUIDE
    -0.98
     pequeno
    -0.96
     posibilidad
    -0.96
    ≲
    -0.96
    POSITIVE LOGITS
     your
    1.64
     that
    1.20
    實現
    1.11
     changed
    1.10
    紀錄
    1.09
    えたら
    1.09
    每個
    1.08
    闡
    1.08
     zaken
    1.06
    しておく
    1.06
    Activations Density 0.023%

    No Known Activations