© 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. 87207
    Prev
    Next
    INDEX
    Explanations

    in-vitro chemical assays

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

    scientific terminology in academic papers, particularly chemical compounds and technical measurements.

    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
     sobot
    -1.19
    @[+][
    -1.12
     trouvent
    -1.12
    outchouc
    -1.09
    niksi
    -1.07
     функция
    -1.07
     penyanyi
    -1.04
     Kontakte
    -1.03
     menyen
    -1.02
     gagné
    -1.02
    POSITIVE LOGITS
    itando
    1.11
     at
    1.04
    getch
    1.02
     improvised
    1.02
     upto
    0.98
     comparatively
    0.97
     distinctly
    0.96
     viz
    0.95
     during
    0.94
     katika
    0.91
    Activations Density 0.057%

    No Known Activations