© 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. 102937
    Prev
    Next
    INDEX
    Explanations

    standard output streams

    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
     descubrió
    -0.73
     uğ
    -0.71
    ayer
    -0.70
     Iraqi
    -0.70
    深度
    -0.69
    彿
    -0.68
     determinations
    -0.68
    atha
    -0.68
    ayar
    -0.66
     Hilbert
    -0.66
    POSITIVE LOGITS
     output
    2.23
     stdout
    2.22
    stdout
    2.02
    stderr
    1.77
     Output
    1.70
     stderr
    1.70
    output
    1.69
    Output
    1.66
     Std
    1.65
     outputs
    1.59
    Activations Density 0.078%

    No Known Activations