© 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. 129703
    Prev
    Next
    INDEX
    Explanations

    code loops and counters

    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
    וּ
    -0.98
    おはようございます
    -0.93
    初めて
    -0.90
    處理
    -0.90
     появилась
    -0.89
    نش
    -0.89
    Mijn
    -0.88
    Ils
    -0.88
     появляется
    -0.88
     ざ
    -0.87
    POSITIVE LOGITS
     until
    1.14
    ailangan
    1.05
     will
    1.04
    invariant
    1.03
     we
    1.02
    endpoint
    1.02
     catholique
    1.02
     prendra
    1.01
     Thần
    1.00
    ztes
    0.98
    Activations Density 0.031%

    No Known Activations