© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93422
    Prev
    Next
    INDEX
    Explanations

    military, security, or geopolitical events

    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
     in
    -3.27
     Although
    -2.70
     When
    -2.66
     Since
    -2.66
     In
    -2.66
     After
    -2.53
     on
    -2.48
     Despite
    -2.48
     As
    -2.45
     There
    -2.42
    POSITIVE LOGITS
     étan
    2.50
     bascul
    2.25
     dezelve
    2.23
    
    2.20
     refroid
    2.20
     zoude
    2.17
     rafraî
    2.17
     rafra
    2.13
     rembour
    2.06
    
    2.06
    Activations Density 0.127%

    No Known Activations