© 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. 44149
    Prev
    Next
    INDEX
    Explanations

    Boehner, Biden, ibuprofen, Fidel

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

    names of political figures or scientific/technical terms.

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

    The neuron is keyed to tokens containing the letter sequence “ide” (e.g. Biden, bidentate, Didelphis).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ”
    -2.70
    '
    -2.64
    当然
    -2.52
    l
    -2.52
    ’
    -2.50
    甚至是
    -2.47
     ideally
    -2.45
    and
    -2.44
    ,"
    -2.42
    内的
    -2.34
    POSITIVE LOGITS
    柃
    2.86
    鹟
    2.80
    桖
    2.38
    ቧ
    2.34
    鞴
    2.34
    猜测
    2.30
    岜
    2.30
    很喜欢
    2.28
     réuss
    2.28
     הוא
    2.28
    Activations Density 0.001%

    No Known Activations