© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43465
    Prev
    Next
    INDEX
    Explanations

    in the

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

    The neuron activates on numeric tokens—whole numbers or decimals—wherever they appear 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
     comprennent
    -1.63
    cs
    -1.44
    筱
    -1.41
     furnishes
    -1.41
     dotyczy
    -1.41
    its
    -1.35
    みてください
    -1.35
     والذي
    -1.33
    ?"
    -1.30
     redan
    -1.30
    POSITIVE LOGITS
     you
    1.77
     name
    1.58
    ’;
    1.55
    ()){
    
    1.52
    を購入
    1.45
    ']=$
    1.41
     embarc
    1.38
     sposob
    1.37
     to
    1.36
    ();
    1.36
    Activations Density 0.053%

    No Known Activations