© 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. 85241
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    The neuron strongly activates on capitalized tokens—proper names (people, places) and all-caps acronyms or technical abbreviations.

    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
    -1.84
    {
    -1.83
    1
    -1.81
     $
    -1.66
    </i>
    -1.60
    ‘
    -1.60
     \
    -1.59
    一個
    -1.58
    '
    -1.58
     drei
    -1.55
    POSITIVE LOGITS
    gucig
    1.68
    hamento
    1.50
    蜴
    1.47
     There
    1.46
    韞
    1.44
     APPROVAL
    1.43
    歘
    1.42
    ꦁ
    1.40
    迩
    1.40
    锵
    1.39
    Activations Density 0.001%

    No Known Activations