© 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. 78849
    Prev
    Next
    INDEX
    Explanations

    European microstates and principalities

    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
    Bleach
    -0.83
    Stamina
    -0.75
    caid
    -0.71
     Brasileira
    -0.69
    Shal
    -0.68
     supported
    -0.66
     Aqui
    -0.64
    绎
    -0.64
     prominent
    -0.63
    auk
    -0.63
    POSITIVE LOGITS
     Andorra
    1.44
     Monaco
    1.37
     Liechtenstein
    1.34
     Princip
    1.09
     princip
    1.09
     sovereign
    1.06
     Vatican
    1.06
    Monaco
    1.05
     micron
    1.03
     Gibraltar
    1.02
    Activations Density 0.031%

    No Known Activations