© 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. 80959
    Prev
    Next
    INDEX
    Explanations

    Hezbollah, Lebanon, Israel

    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
     khuôn
    -0.88
     strikingly
    -0.78
     morto
    -0.78
    atili
    -0.77
     storico
    -0.77
     Dressing
    -0.75
    meln
    -0.74
    ffl
    -0.73
    RUnlock
    -0.73
    PHO
    -0.73
    POSITIVE LOGITS
     Lebanon
    1.50
     Hezbollah
    1.24
     Lebanese
    1.23
    Lebanon
    1.18
     لبنان
    0.92
     Beirut
    0.89
    Leb
    0.85
     Новосибир
    0.82
     Israel
    0.80
    withdrawal
    0.78
    Activations Density 0.018%

    No Known Activations