© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49791
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    oubted
    -0.88
     poetic
    -0.86
     farmhouse
    -0.83
    ໊
    -0.83
    topo
    -0.82
    --
    -0.82
    了些
    -0.81
     automaker
    -0.79
     kezd
    -0.79
    ondale
    -0.78
    POSITIVE LOGITS
     industry
    1.26
     our
    1.06
     industrie
    0.99
    Industry
    0.95
    industry
    0.94
     Industry
    0.93
     healthcare
    0.91
    EMPLO
    0.90
     libere
    0.87
     nossos
    0.86
    Activations Density 0.123%

    No Known Activations