© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75703
    Prev
    Next
    INDEX
    Explanations

    Alex may, Feasibility, A comparison

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

    This neuron is detecting numeric literal tokens (integer, hexadecimal, and floating-point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    1
    -1.62
     I
    -1.60
     $
    -1.54
     or
    -1.48
     эту
    -1.42
    不喜欢
    -1.41
     $\
    -1.41
    などを
    -1.34
    さらに
    -1.33
    5
    -1.30
    POSITIVE LOGITS
    峮
    1.75
     procra
    1.71
     prate
    1.69
     encre
    1.66
     rocha
    1.66
     valuta
    1.66
     Pediat
    1.66
    ⽼
    1.64
     guir
    1.61
     legge
    1.60
    Activations Density 0.002%

    No Known Activations