© 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. 22-GEMMASCOPE-RES-131K
    7. 84297
    Prev
    Next
    INDEX
    Explanations

    web request parameters and ids

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

    The neuron responds to numeric tokens (literal numbers) 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_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
     in
    -1.41
    maining
    -1.37
     gier
    -1.23
     nien
    -1.20
     zwi
    -1.13
     warszawa
    -1.11
    vater
    -1.05
    ourite
    -1.05
     beyond
    -1.02
     hydrauli
    -1.00
    POSITIVE LOGITS
     heutigen
    1.27
     ребенку
    1.23
    根據
    1.14
     shady
    1.13
    本日
    1.12
    本日の
    1.12
    あなたが
    1.11
    譯
    1.11
     modernized
    1.10
    Lors
    1.09
    Activations Density 0.000%

    No Known Activations