© 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. 44190
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude

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

    The neuron activates on numeric tokens—especially decimal or floating-point numbers.

    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
     also
    -1.98
     had
    -1.60
    也
    -1.57
    觥
    -1.51
     was
    -1.49
     as
    -1.48
     cũng
    -1.48
     тоже
    -1.47
     its
    -1.43
    ↵↵
    -1.41
    POSITIVE LOGITS
     crossorigin
    1.51
     Hacer
    1.49
     teraz
    1.48
    𖥧
    1.46
     décontract
    1.46
    ZIONE
    1.45
     Após
    1.45
    ፨
    1.44
     exceptionnel
    1.41
    снимок
    1.41
    Activations Density 0.008%

    No Known Activations