© 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. 66227
    Prev
    Next
    INDEX
    Explanations

    conditional control flow

    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
    也会
    -0.98
     of
    -0.97
    ثم
    -0.94
    chien
    -0.93
     such
    -0.92
    獁
    -0.92
    uitton
    -0.91
    Retrouvez
    -0.90
    <<<<<<<<
    -0.89
     kemudian
    -0.88
    POSITIVE LOGITS
     beide
    1.02
     other
    0.99
     INVENTION
    0.91
     kommet
    0.90
     autres
    0.88
     üçün
    0.85
    IBILITIES
    0.84
     whatever
    0.83
    总是
    0.81
     never
    0.80
    Activations Density 0.005%

    No Known Activations