© 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. 22070
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    The neuron specifically activates on the word “offerings.”

    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
    \
    -3.25
    or
    -2.80
    y
    -2.78
    靓
    -2.44
     машину
    -2.42
     '
    -2.39
    j
    -2.38
     seems
    -2.36
     offers
    -2.25
     {
    -2.14
    POSITIVE LOGITS
    
    2.98
    酲
    2.77
    ⁛
    2.73
    
    2.70
     ſtate
    2.66
     offering
    2.64
    锝
    2.52
    獃
    2.42
     of
    2.41
    聼
    2.41
    Activations Density 0.003%

    No Known Activations