© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78120
    Prev
    Next
    INDEX
    Explanations

    electrical codes and hazardous locations

    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
     phúc
    -0.81
    mery
    -0.80
    bati
    -0.78
    ニム
    -0.77
    にか
    -0.77
    Acetone
    -0.75
    蒔
    -0.74
    线下
    -0.72
     acetone
    -0.72
     držav
    -0.71
    POSITIVE LOGITS
     NEC
    0.94
    Skill
    0.80
    NEC
    0.78
     Article
    0.78
     feeders
    0.77
    Sight
    0.76
    Feed
    0.74
    Iz
    0.73
     CEC
    0.72
    Quiz
    0.71
    Activations Density 0.024%

    No Known Activations