© 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. 34768
    Prev
    Next
    INDEX
    Explanations

    component selectors

    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
     Aún
    -1.48
     Ainda
    -1.24
     Dijo
    -1.20
     Vitamina
    -1.20
     Lleva
    -1.20
     Debido
    -1.15
     做法
    -1.11
     Apesar
    -1.08
     Makefile
    -1.08
     Tienen
    -1.07
    POSITIVE LOGITS
    ,''
    1.16
    。
    1.15
     bzw
    1.14
     ulasan
    1.08
     at
    1.07
     atau
    1.06
     meu
    1.06
     a
    1.05
    ila
    1.04
     به‌عنوان
    1.03
    Activations Density 0.004%

    No Known Activations