© 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. 13574
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

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

    The main thing this neuron does is find numeric literals (tokens consisting of digits or numbers) in code or 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
    lgari
    -0.81
    一天
    -0.80
     new
    -0.79
     föres
    -0.77
    Signin
    -0.77
     berätt
    -0.76
    𝓽
    -0.76
    new
    -0.76
     Es
    -0.75
     für
    -0.74
    POSITIVE LOGITS
    ⱼ
    0.96
     WISCONSIN
    0.92
     reservados
    0.91
    practices
    0.91
    urrent
    0.91
    asje
    0.91
     أص
    0.90
     ILLINOIS
    0.90
    贈
    0.90
     hábitos
    0.89
    Activations Density 0.006%

    No Known Activations