© 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. 71717
    Prev
    Next
    INDEX
    Explanations

    public .css name

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

    The main thing this neuron does is spot standalone 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
     conster
    -1.09
    bouncycastle
    -1.02
    اااا
    -1.00
    AGAIN
    -0.96
    WOMEN
    -0.96
     MainAxisSize
    -0.95
     nullptr
    -0.94
     breakthroughs
    -0.94
     卡通
    -0.94
    Hvis
    -0.93
    POSITIVE LOGITS
     you
    1.80
     your
    1.38
     example
    1.07
    You
    1.00
    As
    0.97
    Here
    0.94
     Whenever
    0.93
     stessa
    0.93
    Example
    0.93
    To
    0.92
    Activations Density 0.097%

    No Known Activations