© 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. 60158
    Prev
    Next
    INDEX
    Explanations

    land and electoral systems

    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
     relativistic
    -0.79
    oose
    -0.77
     wrecks
    -0.76
    ativistic
    -0.74
    licative
    -0.73
    Env
    -0.71
     Bout
    -0.71
     солдат
    -0.71
    绥
    -0.70
    zano
    -0.69
    POSITIVE LOGITS
     land
    1.76
     capture
    1.13
     Land
    1.13
     LAND
    1.11
     capturing
    1.09
    capture
    1.05
    Land
    1.04
     value
    1.04
    土地
    0.99
     landowners
    0.99
    Activations Density 0.016%

    No Known Activations