© 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. 68478
    Prev
    Next
    INDEX
    Explanations

    makes it possible to

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

    The neuron detects phrasing that expresses enabling or feasibility, as in “possible to” or “makes it possible to.”

    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
     it
    -1.76
     '
    -1.70
    </td>
    -1.59
    ers
    -1.55
    ="
    -1.43
    正常的
    -1.42
    ｢
    -1.38
     ''
    -1.37
     as
    -1.35
     utilizar
    -1.32
    POSITIVE LOGITS
    過程
    1.89
     剤
    1.88
    鸶
    1.84
    歺
    1.81
    </h4>
    1.79
    okovic
    1.73
    enging
    1.72
    焄
    1.71
    ographical
    1.70
    istici
    1.69
    Activations Density 0.006%

    No Known Activations