© 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. 111108
    Prev
    Next
    INDEX
    Explanations

    Hurricane Sandy aftermath

    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
     hedges
    -0.90
    ostat
    -0.84
     disgruntled
    -0.83
    ellón
    -0.82
    ganie
    -0.82
    讪
    -0.81
     coraz
    -0.81
     Farewell
    -0.81
    lateinit
    -0.81
    mäßigen
    -0.79
    POSITIVE LOGITS
     rebuilding
    1.98
     disaster
    1.98
     rebuild
    1.95
     recovery
    1.74
     reconstruction
    1.68
     damage
    1.68
     Disaster
    1.56
     FEMA
    1.55
     damaged
    1.50
     relief
    1.49
    Activations Density 0.098%

    No Known Activations