© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26814
    Prev
    Next
    INDEX
    Explanations

    person names

    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
     its
    -1.03
    讳
    -0.82
     everybody
    -0.81
     стадии
    -0.80
     agenda
    -0.78
     Germany
    -0.77
    lution
    -0.77
     tuvimos
    -0.72
    ститу
    -0.72
     some
    -0.72
    POSITIVE LOGITS
     tirs
    0.84
     库存
    0.81
     密
    0.79
    reiras
    0.78
     menores
    0.78
    Cheat
    0.76
     рецепт
    0.76
    frow
    0.75
     beh
    0.75
    TSCA
    0.74
    Activations Density 0.028%

    No Known Activations