© 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. 34-GEMMASCOPE-RES-131K
    4. 12188
    Prev
    Next
    INDEX
    Explanations

    numbers with mathematical operations

    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_34/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
     paie
    -0.82
    ekk
    -0.82
    timore
    -0.81
     corrente
    -0.81
     certes
    -0.80
    nutí
    -0.79
    basePath
    -0.78
     внутренней
    -0.77
    apatilla
    -0.77
     geboren
    -0.77
    POSITIVE LOGITS
     такие
    0.68
    Produce
    0.68
     možné
    0.68
    賽
    0.68
     SDG
    0.67
    Plus
    0.66
     actually
    0.66
     такое
    0.66
     يكون
    0.66
    యా
    0.65
    Activations Density 0.037%

    No Known Activations