© 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. 27017
    Prev
    Next
    INDEX
    Explanations

    medical or technical queries

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

    new paragraphs or line breaks in structured documents.

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

    The neuron activates on numeric citation markers (the bracketed reference numbers in the text).

    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
     have
    -1.19
    ！！！！
    -1.17
     that
    -1.16
     what
    -1.16
     start
    -1.13
     abril
    -1.13
    Having
    -1.12
     Makanan
    -1.12
    Without
    -1.10
    While
    -1.09
    POSITIVE LOGITS
    pherds
    1.16
     portefeuille
    1.13
     partenariat
    1.09
    oczes
    1.07
    flox
    1.04
    maining
    1.03
     dando
    1.03
     verwe
    1.01
     technische
    1.00
    lel
    0.99
    Activations Density 0.000%

    No Known Activations