© 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. 82640
    Prev
    Next
    INDEX
    Explanations

    materials and techniques

    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
    materials
    -1.30
     Materials
    -1.30
     MATERIALS
    -1.30
     materiales
    -1.23
    Materials
    -1.19
    素材
    -1.14
    材料
    -1.13
     materi
    -1.12
     materials
    -1.11
     Materialien
    -1.08
    POSITIVE LOGITS
     finish
    1.27
     finished
    1.21
     finishing
    1.11
     finishes
    1.06
     dyes
    0.88
    finished
    0.85
    finish
    0.83
     processing
    0.81
     tools
    0.79
    辅
    0.79
    Activations Density 0.036%

    No Known Activations