© 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. 38315
    Prev
    Next
    INDEX
    Explanations

    Age as

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

    The neuron activates on numeric tokens (digit sequences) in documents.

    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
     even
    -1.53
     its
    -1.40
     just
    -1.14
     it
    -1.10
     in
    -1.07
     by
    -1.04
     ever
    -1.04
     only
    -1.00
     merely
    -0.98
     there
    -0.97
    POSITIVE LOGITS
     frontières
    1.09
     ซึ่ง
    1.05
    Ancien
    1.01
     périodes
    1.00
     espesor
    0.99
    jusqu
    0.98
     โดย
    0.98
    vgl
    0.96
     których
    0.96
    forgot
    0.94
    Activations Density 0.000%

    No Known Activations