© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66238
    Prev
    Next
    INDEX
    Explanations

    Madrid Prepare / The following

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

    The neuron strongly activates on numeric tokens (digits and numbers) within arithmetic or base‐conversion expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Shortly
    -0.94
    経営
    -0.91
    rét
    -0.90
    utusan
    -0.88
     Shortly
    -0.88
    情報の
    -0.84
     two
    -0.82
    Beschreibung
    -0.82
    Through
    -0.81
    家電
    -0.80
    POSITIVE LOGITS
    crazy
    1.00
     všetkých
    0.94
    fillment
    0.91
     ainsi
    0.90
    wants
    0.88
     kaikk
    0.87
     potrebné
    0.85
    स्या
    0.84
    emballage
    0.84
    arum
    0.84
    Activations Density 0.063%

    No Known Activations