© 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. 84180
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematics or science

    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
     statistically
    -2.41
     statistics
    -2.16
     statistical
    -1.99
    Statistics
    -1.87
     stats
    -1.86
     статисти
    -1.85
     statistic
    -1.85
    statistical
    -1.84
     Statistics
    -1.82
    統計
    -1.80
    POSITIVE LOGITS
    Melting
    0.81
     église
    0.68
    Sven
    0.66
    ٲ
    0.65
    pyrid
    0.65
    oose
    0.65
     Prefeitura
    0.65
     probability
    0.65
     rainha
    0.65
     supre
    0.64
    Activations Density 0.031%

    No Known Activations