© 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. 7641
    Prev
    Next
    INDEX
    Explanations

    encrustation or engagement

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

    The neuron responds to common morphological affixes—particularly the “en-” prefix and noun/verb-forming suffixes like “-ment,” “-ation,” and “-ing.”

    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
    C
    -3.50
    H
    -2.78
    ᠂
    -2.77
    L
    -2.72
    N
    -2.58
    M
    -2.53
    ⸰
    -2.44
     oração
    -2.36
    F
    -2.34
    '
    -2.30
    POSITIVE LOGITS
    ми
    2.55
     This
    2.55
     Now
    2.53
    欵
    2.41
     Not
    2.38
    沕
    2.34
    
    2.33
    踅
    2.30
    灕
    2.23
     Which
    2.19
    Activations Density 0.026%

    No Known Activations