© 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. 103697
    Prev
    Next
    INDEX
    Explanations

    county court new jersey

    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
    Queens
    -0.82
    OfDay
    -0.73
     Fernandes
    -0.72
    袜
    -0.71
     redesign
    -0.69
    лас
    -0.68
     Queens
    -0.68
    addAll
    -0.66
    зам
    -0.66
    opengl
    -0.66
    POSITIVE LOGITS
    medico
    0.85
    dod
    0.85
     boarded
    0.81
    bihi
    0.81
     Determining
    0.81
     mutilated
    0.79
     Fourteen
    0.77
    🪩
    0.76
     highschool
    0.75
     indented
    0.72
    Activations Density 0.037%

    No Known Activations