© 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. 10-GEMMASCOPE-RES-131K
    7. 69633
    Prev
    Next
    INDEX
    Explanations

    Ferdinand and phosphorylation

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

    The neuron detects names with "Ferdinand" or technical terms related to "phosphorylation".

    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
    栳
    -3.33
    '
    -3.17
    的
    -3.17
    乆
    -3.14
    Ꮔ
    -3.08
    琑
    -3.03
    ﮟ
    -3.02
    卝
    -3.00
    亖
    -2.92
    out
    -2.89
    POSITIVE LOGITS
     and
    3.31
     of
    3.13
     You
    2.64
    ).
    2.61
     In
    2.56
    ↵
    2.48
     They
    2.47
     After
    2.33
     Following
    2.28
    讴
    2.27
    Activations Density 0.025%

    No Known Activations