© 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. 22-GEMMASCOPE-RES-131K
    7. 501
    Prev
    Next
    INDEX
    Explanations

    chemical elements and constituents

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

    chemical and scientific content related to elements, acids, and compounds in analytical studies.

    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
     or
    -1.52
     on
    -1.30
     can
    -1.15
     with
    -1.08
     requer
    -1.05
     procedures
    -1.05
    fü
    -1.05
     profundo
    -1.05
     does
    -1.04
     before
    -1.04
    POSITIVE LOGITS
     démoc
    1.11
     verschillende
    1.11
     conocido
    1.11
    这么多
    1.10
     conhecido
    1.07
     conocidas
    1.07
     étages
    1.05
     zugelassen
    1.04
     verantwortlich
    1.02
     mélang
    1.02
    Activations Density 0.154%

    No Known Activations