© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98082
    Prev
    Next
    INDEX
    Explanations

    license and copyright text

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

    This neuron activates on standalone numeric tokens (e.g., version numbers, years, counts) in code or comment 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_34/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
     by
    -1.42
     their
    -1.41
     so
    -1.32
     had
    -1.20
    ！(
    -1.19
     strangely
    -1.18
     Despite
    -1.17
     supremely
    -1.15
     Surprisingly
    -1.13
     Almost
    -1.10
    POSITIVE LOGITS
     goofy
    1.16
     dreary
    1.13
     predominantly
    1.13
     horrid
    1.13
     abd
    1.08
    ,;
    1.08
    ⎯
    1.08
     alcuni
    1.07
     crucial
    1.07
     boister
    1.05
    Activations Density 0.001%

    No Known Activations