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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66254
    Prev
    Next
    INDEX
    Explanations

    biological and medical fields

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

    academic journal titles or scientific publication names in citations.

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

    The main thing this neuron does is detect tokens that are part of journal or publication names in reference lists.

    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
     you
    -1.73
     your
    -1.67
     it
    -1.34
     teritor
    -1.26
     will
    -1.23
    neous
    -1.23
     some
    -1.22
     punya
    -1.20
     another
    -1.20
     there
    -1.20
    POSITIVE LOGITS
     Жа
    1.31
    Materiál
    1.24
     různ
    1.16
    当我
    1.16
     contextLoads
    1.12
     čty
    1.12
     olika
    1.09
     často
    1.08
     skuto
    1.08
    を搭載
    1.07
    Activations Density 0.015%

    No Known Activations