© 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. 10-GEMMASCOPE-RES-131K
    7. 99090
    Prev
    Next
    INDEX
    Explanations

    expression of

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

    The neuron detects the phrase "Expression of" at the beginning of scientific paper titles.

    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_10/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
    
    -2.67
    鯷
    -2.59
    ſſen
    -2.31
    骉
    -2.27
    ༈
    -2.25
    ㋛
    -2.23
     incredibly
    -2.23
    鵙
    -2.22
    媜
    -2.22
     the
    -2.20
    POSITIVE LOGITS
    “
    3.28
    灕
    2.48
     Often
    2.31
     keben
    2.22
    ,
    2.09
    ～～
    2.02
    Often
    2.02
     After
    2.00
     Though
    1.98
    Because
    1.97
    Activations Density 0.080%

    No Known Activations