© 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. 63484
    Prev
    Next
    INDEX
    Explanations

    state-run China

    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
    midt
    -1.05
    rh
    -0.85
     במק
    -0.82
     Obama
    -0.81
     Fiscal
    -0.80
     saisie
    -0.78
     argv
    -0.77
     лидер
    -0.77
     Tamil
    -0.76
    Ö
    -0.76
    POSITIVE LOGITS
     Ministry
    0.97
    Ministry
    0.87
     ministry
    0.87
     rutin
    0.80
     controllable
    0.78
     state
    0.74
    例
    0.74
    ִּ
    0.73
     souverain
    0.72
     Wam
    0.72
    Activations Density 0.014%

    No Known Activations