© 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. 7023
    Prev
    Next
    INDEX
    Explanations

    measurement of displacement

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

    The neuron primarily activates on numeric tokens (i.e. any numbers or measured values) in the text.

    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
    她
    -3.17
    籥
    -2.95
    懌
    -2.95
    锷
    -2.89
    ╿
    -2.78
    ᨆ
    -2.66
     poupée
    -2.63
    😫
    -2.59
    韩国
    -2.53
    '))
    -2.53
    POSITIVE LOGITS
    2
    3.91
    ]
    3.61
    3
    3.42
     \
    3.08
    0
    3.06
    8
    3.05
    5
    3.03
    6
    2.95
    ']
    2.92
    9
    2.89
    Activations Density 0.003%

    No Known Activations