© 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. 475
    Prev
    Next
    INDEX
    Explanations

    javascript, matlab, sql, python dataframes

    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
    Эти
    -1.55
    这两个
    -1.54
    这两
    -1.54
    Both
    -1.52
     Both
    -1.38
    These
    -1.38
     Эти
    -1.38
     этих
    -1.36
    これらの
    -1.34
    these
    -1.33
    POSITIVE LOGITS
    tesse
    0.97
    Autowired
    0.89
    ്ട
    0.86
    ТА
    0.85
    └──
    0.85
    seteq
    0.84
    }=\
    0.82
    다
    0.80
     Keynote
    0.80
    mment
    0.80
    Activations Density 0.070%

    No Known Activations