© 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. 118039
    Prev
    Next
    INDEX
    Explanations

    FEMA flood response

    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
    Voto
    -0.73
     laid
    -0.71
     dày
    -0.69
     whirl
    -0.67
    timmen
    -0.66
    
    -0.66
     settler
    -0.65
    lectual
    -0.64
     confiscation
    -0.64
    PPT
    -0.64
    POSITIVE LOGITS
     Flood
    1.82
    Flood
    1.76
     flood
    1.73
    flood
    1.48
     FLOOD
    1.38
     floodplain
    1.37
     flooding
    1.35
     FEMA
    1.30
     FIRM
    1.14
     floods
    1.12
    Activations Density 0.009%

    No Known Activations