© 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. 87123
    Prev
    Next
    INDEX
    Explanations

    decided court decisions

    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
    kaitan
    -0.77
    ью
    -0.75
     Variation
    -0.74
    視聴
    -0.74
    àu
    -0.73
    Stride
    -0.73
     Conjug
    -0.73
    äfts
    -0.71
     detect
    -0.70
    чем
    -0.70
    POSITIVE LOGITS
    decided
    1.10
     Decided
    1.09
     decisions
    1.09
    Decided
    1.09
     decision
    1.05
    gued
    1.05
     decisiones
    1.02
     decided
    1.01
     Supreme
    0.99
     decisione
    0.98
    Activations Density 1.229%

    No Known Activations