© 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. 67718
    Prev
    Next
    INDEX
    Explanations

    code, question, or tag labels

    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
     oameni
    -1.23
    :—
    -1.17
     Meksi
    -1.07
     kuh
    -1.06
     benefícios
    -1.05
     देने
    -1.05
     construida
    -1.05
     requerido
    -1.04
     precedenti
    -1.03
     creado
    -1.02
    POSITIVE LOGITS
    *@
    0.97
     leider
    0.93
     arrange
    0.91
    ürger
    0.89
    errcode
    0.89
    proteins
    0.87
    <strong>
    0.87
    先生が
    0.87
     Hastings
    0.84
    </em>
    0.84
    Activations Density 0.000%

    No Known Activations