© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76855
    Prev
    Next
    INDEX
    Explanations

    legal judgment or sentence

    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
    leville
    -0.80
    regas
    -0.78
     Phillip
    -0.76
     logos
    -0.73
    🥪
    -0.72
    Dagger
    -0.72
    主催
    -0.71
     sprints
    -0.71
    明る
    -0.71
    땅
    -0.71
    POSITIVE LOGITS
     judgment
    2.09
     entered
    1.84
     Judgment
    1.69
    judgment
    1.55
     judgement
    1.52
    Judgment
    1.45
     judgments
    1.45
     entry
    1.43
     decree
    1.38
    Entry
    1.36
    Activations Density 0.147%

    No Known Activations