© 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. 49072
    Prev
    Next
    INDEX
    Explanations

    air emission source and transport

    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
    Oxygen
    -0.81
    oxygen
    -0.77
     coming
    -0.75
     Take
    -0.73
     Oxygen
    -0.72
    藻
    -0.72
    JNIEnv
    -0.72
     Tween
    -0.71
    સ્
    -0.71
    Unemployment
    -0.71
    POSITIVE LOGITS
     receptors
    1.20
     receptor
    1.17
     meteorological
    1.03
    receptor
    1.03
     terrain
    0.99
     Receptor
    0.96
    winds
    0.94
    stack
    0.93
     stack
    0.91
     SCREEN
    0.89
    Activations Density 0.005%

    No Known Activations