© 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. 112514
    Prev
    Next
    INDEX
    Explanations

    such as specific items

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

    The neuron detects words and phrases that introduce examples or comparisons (e.g. “as,” “such as,” “namely,” “like”).

    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
     or
    -1.90
    h
    -1.69
     it
    -1.62
     luxem
    -1.46
    ulfon
    -1.46
     engel
    -1.42
     hoga
    -1.41
    😜
    -1.39
    💞
    -1.38
    🤙
    -1.37
    POSITIVE LOGITS
    gorro
    2.41
     zatem
    2.16
    őre
    1.86
     temáticas
    1.78
     promesas
    1.76
     Якщо
    1.74
     wtedy
    1.74
     naszej
    1.71
     όταν
    1.70
    私たちの
    1.70
    Activations Density 0.190%

    No Known Activations