© 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. 66708
    Prev
    Next
    INDEX
    Explanations

    scientific classification and definitions

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

    conjunctions (like "and," "but," "because," "with") at the beginning of clauses in academic 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_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
     you
    -1.27
     exhilarating
    -1.09
     astounding
    -1.09
     delightfully
    -1.09
     astonishing
    -1.06
    eqref
    -1.06
     magnificent
    -1.06
     ":
    -1.05
    凭借
    -1.04
     studia
    -1.04
    POSITIVE LOGITS
    -
    1.25
    /
    1.25
     that
    1.09
     this
    1.02
     incluem
    0.97
    !
    0.93
    十二月
    0.92
     also
    0.91
     on
    0.90
     both
    0.89
    Activations Density 0.095%

    No Known Activations