© 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. 545
    Prev
    Next
    INDEX
    Explanations

    Israeli Gaza conflict

    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
     resourceCulture
    -0.75
    }]
    -0.75
     firearm
    -0.73
     aplicable
    -0.72
    BNP
    -0.71
    IONAL
    -0.71
    inalis
    -0.70
    धार
    -0.70
     afforded
    -0.69
     Grote
    -0.69
    POSITIVE LOGITS
     IDF
    0.97
     Gaza
    0.83
     flo
    0.81
     varn
    0.81
     moul
    0.76
    ولوژی
    0.76
    Israel
    0.73
    ission
    0.72
     Israel
    0.72
    multirow
    0.72
    Activations Density 0.017%

    No Known Activations