© 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. 10-GEMMASCOPE-RES-131K
    7. 42581
    Prev
    Next
    INDEX
    Explanations

    voting and polling places

    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_10/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
    which
    -1.14
    它
    -1.10
     its
    -1.09
    ↵
    -1.09
    
    -1.06
     prêtres
    -1.04
    luan
    -1.03
    spheric
    -1.02
    QUID
    -1.02
    essages
    -1.00
    POSITIVE LOGITS
     during
    1.30
     because
    1.22
    その他の
    1.20
     votar
    1.19
     while
    1.17
     when
    1.13
    Ꮗ
    1.13
    韫
    1.12
     time
    1.09
    凜
    1.09
    Activations Density 0.036%

    No Known Activations