© 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. 99162
    Prev
    Next
    INDEX
    Explanations

    van der Waals and related

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

    The neuron detects "van der" or "der" in names, particularly in scientific contexts like "van der Waals" interactions or proper names.

    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
    Ⲉ
    -2.81
    e
    -2.53
    n
    -2.48
    g
    -2.39
    <bos>
    -2.33
    
    -2.22
    O
    -2.14
     борьбе
    -2.13
    U
    -2.06
    v
    -2.05
    POSITIVE LOGITS
    der
    2.89
    щиеся
    2.58
    ра
    2.45
     Endlich
    2.45
     soooo
    2.34
     testigos
    2.34
     quisiera
    2.25
    问道
    2.25
     haces
    2.22
    $,
    2.19
    Activations Density 0.028%

    No Known Activations