© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39094
    Prev
    Next
    INDEX
    Explanations

    a the

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

    This neuron activates strongly on numeric tokens (including integers and decimals), i.e. it detects numbers or measurements 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
     other
    -1.89
     additional
    -1.66
     verbess
    -1.51
     bedeut
    -1.42
     adding
    -1.41
     questionable
    -1.38
    関連リンク
    -1.36
     Aufenthalt
    -1.34
    翾
    -1.34
     wiederhol
    -1.32
    POSITIVE LOGITS
    iffance
    1.72
    6
    1.58
     enam
    1.54
    雖然
    1.34
    7
    1.29
    '];
    1.29
    虽然
    1.28
    despite
    1.28
    WebServlet
    1.27
     myriad
    1.27
    Activations Density 0.117%

    No Known Activations