© 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. 78203
    Prev
    Next
    INDEX
    Explanations

    legislative bodies and officials

    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
     chelsea
    -0.73
    Ʋ
    -0.71
    Tarea
    -0.69
    feuer
    -0.68
    üren
    -0.68
    estimating
    -0.67
     Rump
    -0.66
    час
    -0.66
     illustrationer
    -0.66
    erede
    -0.66
    POSITIVE LOGITS
     House
    0.89
     explanatory
    0.83
     餐
    0.83
     minority
    0.82
     eyebrows
    0.80
     पार
    0.79
     Minority
    0.79
     opposition
    0.78
     floor
    0.77
     Speaker
    0.77
    Activations Density 0.011%

    No Known Activations