© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    probation or parole hearings

    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
    thermia
    -0.82
    entials
    -0.78
    慢慢的
    -0.77
     gây
    -0.76
    preferred
    -0.76
     仁
    -0.71
    oarece
    -0.70
    到底是
    -0.69
     Mystic
    -0.69
    vní
    -0.69
    POSITIVE LOGITS
     supervision
    1.66
     probation
    1.55
     parole
    1.52
     supervised
    1.45
     Supervision
    1.43
    Supervision
    1.34
    supervised
    1.23
     supervising
    1.13
     supervise
    1.10
     supervis
    1.06
    Activations Density 0.028%

    No Known Activations