© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72909
    Prev
    Next
    INDEX
    Explanations

    PubMed searches

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

    database names and scientific citation sources like MEDLINE, PubMed, and EMBASE.

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

    The neuron fires on mentions of bibliographic database names (e.g. PubMed, Embase, MEDLINE, Cochrane Central Register) in research‐methods sections.

    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
     that
    -1.46
     —
    -1.33
     sebuah
    -1.30
     already
    -1.23
    DataInputStream
    -1.21
     ;
    -1.20
     which
    -1.18
    //{
    -1.18
     in
    -1.17
     when
    -1.17
    POSITIVE LOGITS
     れる
    1.48
    왠
    1.34
    뭘
    1.32
     پنجم
    1.27
     réglable
    1.27
     matériaux
    1.27
     disques
    1.26
    늠
    1.17
    總是
    1.15
     основном
    1.14
    Activations Density 0.212%

    No Known Activations