© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    Highway planners, vehicles

    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
     ober
    -0.86
    🍧
    -0.70
     fisk
    -0.70
     verf
    -0.69
     freezes
    -0.68
     setUsername
    -0.68
     Languedoc
    -0.67
     awak
    -0.67
     verm
    -0.67
    寰
    -0.66
    POSITIVE LOGITS
    🎳
    0.96
    质量
    0.95
     Qualitäts
    0.85
    FEE
    0.82
    threat
    0.81
     independence
    0.81
     threats
    0.81
    niko
    0.80
    Fees
    0.79
    fees
    0.79
    Activations Density 0.013%

    No Known Activations