© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25712
    Prev
    Next
    INDEX
    Explanations

    Effect of, Q:, i =

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

    This neuron activates on the word “to,” especially when it’s the infinitive marker.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     シリーズ
    -1.22
    シリーズ
    -1.18
     tehd
    -1.13
     เพราะ
    -1.10
    了自己
    -1.05
     Isso
    -1.01
     ilusión
    -1.00
     wensen
    -0.99
    فایل
    -0.99
     lã
    -0.99
    POSITIVE LOGITS
     to
    1.45
     new
    1.30
     of
    1.23
     as
    1.13
     in
    1.06
     neuer
    1.05
    </h2>
    0.99
    .
    0.98
     used
    0.98
     who
    0.97
    Activations Density 0.000%

    No Known Activations