© 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. 117957
    Prev
    Next
    INDEX
    Explanations

    "THE KEY" or "Background"

    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
    limo
    -0.82
    рѣ
    -0.73
     doméstico
    -0.73
    knię
    -0.72
     concede
    -0.71
    documento
    -0.70
    个数
    -0.68
    jre
    -0.68
     clause
    -0.68
     Mitt
    -0.67
    POSITIVE LOGITS
     Ihrer
    0.89
    IFORM
    0.85
     meste
    0.83
    lowski
    0.82
    utilizzo
    0.81
     Promote
    0.80
     herab
    0.80
    SetItem
    0.79
     deiner
    0.79
     erforderlich
    0.76
    Activations Density 0.002%

    No Known Activations