© 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. 69031
    Prev
    Next
    INDEX
    Explanations

    code or questions

    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
    alami
    -1.04
     exceptions
    -1.01
     заболеваний
    -0.97
    verbs
    -0.96
     his
    -0.94
    jasa
    -0.93
     how
    -0.92
    detek
    -0.92
     to
    -0.91
    kona
    -0.91
    POSITIVE LOGITS
    خرى
    1.08
    こちらも
    1.06
    condido
    1.06
    你还
    1.06
    これも
    1.05
    你现在
    1.05
     nuevamente
    1.04
     Again
    1.04
    了一眼
    1.04
     $-.
    1.03
    Activations Density 0.000%

    No Known Activations