© 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. 113587
    Prev
    Next
    INDEX
    Explanations

    different categories

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

    The neuron activates on the adjective “different.”

    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
    ’
    -1.57
    :
    -1.48
     at
    -1.41
    {
    -1.37
     الوزراء
    -1.37
       
    -1.35
    —
    -1.35
    <
    -1.34
     When
    -1.33
    ebenarnya
    -1.33
    POSITIVE LOGITS
    泐
    1.59
    нодоро
    1.55
     are
    1.53
    0
    1.52
    rebro
    1.50
    埏
    1.47
     ingenting
    1.43
    瘪
    1.40
     you
    1.39
    ны
    1.38
    Activations Density 0.009%

    No Known Activations