© 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. 127742
    Prev
    Next
    INDEX
    Explanations

    showing or presenting information

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

    The neuron activates on numeric tokens—especially decimal values and other quantitative references 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
     couldn
    -1.66
     didn
    -1.58
    vocations
    -1.55
     какво
    -1.44
     It
    -1.41
     it
    -1.36
    担任
    -1.35
     have
    -1.34
     hilft
    -1.34
     şeyi
    -1.34
    POSITIVE LOGITS
    ELTS
    1.53
     weiße
    1.48
    给她
    1.45
     Italie
    1.41
    carus
    1.36
     elektrische
    1.35
    给他们
    1.33
    +++++
    1.31
    ——”
    1.31
    )”
    1.31
    Activations Density 0.061%

    No Known Activations