© 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. 7743
    Prev
    Next
    INDEX
    Explanations

    phrases with whereby

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

    The neuron fires most strongly on short function words—especially common three‐ or four‐letter prepositions or articles (e.g. German “bei,” “der,” Danish “ved,” Slovenian “pri,” etc.).

    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
    ’
    -2.66
    '
    -2.63
    {
    -2.05
    is
    -2.00
     in
    -1.88
    .
    -1.77
    )
    -1.73
     has
    -1.70
    ."
    -1.66
    \
    -1.66
    POSITIVE LOGITS
     our
    2.14
    峮
    1.91
    膘
    1.82
    玙
    1.80
    はは
    1.80
    沨
    1.79
    ของ
    1.74
    琬
    1.70
    elerik
    1.69
    entado
    1.67
    Activations Density 0.002%

    No Known Activations