© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16476
    Prev
    Next
    INDEX
    Explanations

    scientific abbreviations and symbols

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

    bibliographic citation elements like dashes, journal names, and author initials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by hyphens or dash characters used in hyphenated words or compounds.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     on
    -1.13
     by
    -1.06
    cubes
    -1.05
     technological
    -1.05
     sopa
    -1.03
     one
    -1.02
     clara
    -1.02
     novela
    -1.02
    },[])
    -1.01
     can
    -1.00
    POSITIVE LOGITS
     sám
    1.09
     integriert
    1.09
     bestanden
    1.08
     geladen
    1.05
     Announces
    1.05
     insi
    1.02
     間取り
    1.01
     principalement
    0.99
     小学生
    0.98
     uží
    0.98
    Activations Density 0.003%

    No Known Activations