© 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. 36566
    Prev
    Next
    INDEX
    Explanations

    null or none values

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

    The neuron is primarily activated by numeric literals (tokens composed of digits, possibly with decimal points) 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
    过来了
    -0.82
     arbetar
    -0.79
     overthrown
    -0.76
     Pepsi
    -0.75
     starten
    -0.73
    嬪
    -0.73
    稲田
    -0.73
     mendorong
    -0.72
    oncé
    -0.72
    參考文獻
    -0.72
    POSITIVE LOGITS
     null
    1.38
     none
    1.10
     None
    1.03
     NULL
    1.01
     Null
    0.99
    NULL
    0.92
     вовсе
    0.91
    None
    0.91
     spécial
    0.91
     no
    0.88
    Activations Density 0.030%

    No Known Activations