© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39694
    Prev
    Next
    INDEX
    Explanations

    method invocation or creation

    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
     been
    -1.03
     vectorielles
    -1.02
    눙
    -0.97
     hien
    -0.92
    −/−
    -0.90
     HÀ
    -0.89
     $_=
    -0.88
     krak
    -0.88
    INCLUD
    -0.85
     neither
    -0.85
    POSITIVE LOGITS
     brazo
    0.97
     new
    0.97
     появится
    0.96
    Теле
    0.95
     AppCompatTheme
    0.92
    äte
    0.90
    שלום
    0.90
    itize
    0.89
    Builder
    0.88
     indulging
    0.87
    Activations Density 0.004%

    No Known Activations