© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    chemical extraction and separation

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

    chemical extraction processes and solvents in scientific procedures.

    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_22/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
     they
    -1.26
     vaše
    -1.23
     Bakterien
    -1.17
     szerző
    -1.16
     that
    -1.16
     their
    -1.15
     your
    -1.13
     trasera
    -1.10
     this
    -1.09
     هوشمند
    -1.09
    POSITIVE LOGITS
    Beschrijving
    1.05
    Răsp
    1.05
     يكن
    1.01
     anschließend
    1.01
     then
    1.01
    は以下の
    1.00
    Koordin
    1.00
     buvo
    0.99
    Dispon
    0.98
     насеља
    0.96
    Activations Density 0.003%

    No Known Activations