© 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. 94005
    Prev
    Next
    INDEX
    Explanations

    terrorism, bomb, explosion

    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
     skyl
    -0.84
     syndicated
    -0.78
    CoA
    -0.77
     initialization
    -0.77
     unifor
    -0.75
     joc
    -0.75
     Accounting
    -0.75
     Initialization
    -0.74
     drug
    -0.74
    🚸
    -0.73
    POSITIVE LOGITS
    Terror
    1.00
     terrorism
    0.80
     explosion
    0.79
    Monarch
    0.79
    terrorism
    0.77
    ourite
    0.76
    terror
    0.75
    bomb
    0.74
    Frontier
    0.74
    Bung
    0.73
    Activations Density 0.019%

    No Known Activations