© 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. 73679
    Prev
    Next
    INDEX
    Explanations

    things required

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

    The neuron fires on occurrences of the word “mandatory,” i.e. it flags explicit mentions of requirements or obligations.

    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
     '
    -3.44
     The
    -3.09
    änemark
    -2.84
     แต่
    -2.81
     \"
    -2.80
    🫅
    -2.77
    都想
    -2.63
    
    -2.61
    ykjav
    -2.58
     เมื่อ
    -2.48
    POSITIVE LOGITS
    1
    3.22
    趼
    2.98
    the
    2.94
    Even
    2.88
    ”,
    2.88
    縯
    2.81
    ～　
    2.75
    ↵
    2.72
    ⽌
    2.70
    With
    2.63
    Activations Density 0.001%

    No Known Activations