© 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. 109511
    Prev
    Next
    INDEX
    Explanations

    states and their entities

    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
    _));
    -0.92
    Ende
    -0.89
    SPECIFICATIONS
    -0.83
     страны
    -0.82
     sacar
    -0.81
    注釈
    -0.79
    Tanggal
    -0.77
    indonesia
    -0.76
     วัน
    -0.76
    rašymas
    -0.76
    POSITIVE LOGITS
     State
    1.71
     state
    1.51
     Governor
    1.40
     Department
    1.38
     governor
    1.26
    州
    1.21
     Avenue
    1.19
    State
    1.17
     legislature
    1.17
     Legislature
    1.14
    Activations Density 0.093%

    No Known Activations