© 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. 65735
    Prev
    Next
    INDEX
    Explanations

    assertThat assertion

    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
    former
    -0.81
    Texas
    -0.79
    veh
    -0.75
    persist
    -0.75
     Belize
    -0.75
    xhttp
    -0.74
     Kuwait
    -0.74
     VEHICLE
    -0.73
    dict
    -0.72
     Karnataka
    -0.72
    POSITIVE LOGITS
    assertThat
    1.09
     Forsyth
    0.82
     modal
    0.78
     Hamster
    0.75
    (´
    0.73
    lägen
    0.72
    COMMERCIAL
    0.69
     Fatal
    0.69
     Tän
    0.69
    བྱ
    0.69
    Activations Density 0.007%

    No Known Activations