© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84210
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    就像是
    -0.96
     dziecko
    -0.91
    の方も
    -0.90
    </strong>
    -0.89
     you
    -0.89
    ように
    -0.87
     będ
    -0.85
     silencioso
    -0.85
    際には
    -0.84
    相对
    -0.83
    POSITIVE LOGITS
     tênis
    0.98
     Esa
    0.95
     colesterol
    0.93
     lipca
    0.92
    ukkan
    0.91
    бурга
    0.90
    <bos>
    0.90
    nerstag
    0.89
     连接
    0.87
     ruptura
    0.87
    Activations Density 0.040%

    No Known Activations