© 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. 58295
    Prev
    Next
    INDEX
    Explanations

    measurement in units

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

    The neuron primarily detects floating‐point numeric literals (numbers containing a decimal point).

    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
     that
    -2.06
    :
    -1.85
     name
    -1.70
    although
    -1.54
    を迎
    -1.48
     of
    -1.47
    وفق
    -1.45
    駭
    -1.45
     C
    -1.42
    name
    -1.38
    POSITIVE LOGITS
     bebes
    1.64
     negru
    1.62
    </h4>
    1.61
     interfaz
    1.58
    </h5>
    1.55
    狁
    1.55
    癀
    1.50
    菝
    1.50
    </u>
    1.48
     alpes
    1.45
    Activations Density 0.002%

    No Known Activations