© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84013
    Prev
    Next
    INDEX
    Explanations

    designed by or for

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

    The neuron activates on uses of the word “designed,” marking when something’s design attribution or design process is being described.

    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
    ৹
    -2.67
    樒
    -2.42
    {
    -2.28
    푘
    -2.25
    ᡴ
    -2.22
    ⟐
    -2.22
    鹛
    -2.20
    ープン
    -2.20
    槩
    -2.17
    ClassNotFound
    -2.16
    POSITIVE LOGITS
    '
    3.05
     —
    2.59
    椟
    2.55
     he
    2.47
    刋
    2.31
     –
    2.31
     ältere
    2.27
    而又
    2.27
     They
    2.19
     marched
    2.19
    Activations Density 0.015%

    No Known Activations