© 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. 78225
    Prev
    Next
    INDEX
    Explanations

    materials and compounds

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical formulas and compound names in scientific materials research papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    uzen
    -0.79
    桓
    -0.78
     polycarbonate
    -0.78
     visco
    -0.75
     ujian
    -0.74
     elast
    -0.73
    руб
    -0.73
     hydrocarbons
    -0.72
     bě
    -0.72
    벡터
    -0.72
    POSITIVE LOGITS
     phases
    1.53
     compounds
    1.42
     materials
    1.37
    phases
    1.37
     compound
    1.36
     phase
    1.33
    phase
    1.22
     material
    1.19
     Phases
    1.15
    Phases
    1.13
    Activations Density 0.185%

    No Known Activations