© 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. 68924
    Prev
    Next
    INDEX
    Explanations

    programming class definitions

    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
     Th
    -0.94
     boden
    -0.89
     praticamente
    -0.89
     praktisch
    -0.88
     вся
    -0.86
    BTW
    -0.84
     bénéficient
    -0.83
     Rechten
    -0.82
     elegant
    -0.81
    феры
    -0.81
    POSITIVE LOGITS
     from
    1.20
    さんです
    1.10
    Màu
    1.09
    œ
    1.09
    Sản
    1.08
     normalt
    1.07
    ₨
    1.05
     Disabilities
    1.05
    tembro
    1.04
    ऑ
    1.03
    Activations Density 0.040%

    No Known Activations