© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108527
    Prev
    Next
    INDEX
    Explanations

    AML & Verification

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

    This neuron detects document-structure markers such as section headings, labels, enumeration numbers, colons, and punctuation that organize the layout.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ကိုးကား
    -1.06
     Име
    -0.99
    而不是
    -0.96
     kwiaty
    -0.91
    髂
    -0.89
     கா
    -0.89
     gminy
    -0.88
     มัน
    -0.88
     ὁ
    -0.85
    狨
    -0.85
    POSITIVE LOGITS
    логов
    1.08
     would
    1.06
    requisite
    1.00
    нем
    0.98
     courier
    0.96
    :"",
    0.96
    براير
    0.90
    fó
    0.90
    timation
    0.88
    теле
    0.88
    Activations Density 0.057%

    No Known Activations