© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77803
    Prev
    Next
    INDEX
    Explanations

    software licenses

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

    The neuron is triggered by non-prose tokens used for code/comment formatting—things like asterisks in comment blocks, punctuation or operator symbols (e.g. “=”), and numeric literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     convert
    -0.81
    线上
    -0.79
    convert
    -0.76
     soft
    -0.75
    热的
    -0.75
    网友
    -0.72
    动
    -0.72
     samodziel
    -0.69
    ļas
    -0.69
    -"
    -0.69
    POSITIVE LOGITS
    ytu
    0.96
    吩咐
    0.88
     pou
    0.88
    ꒦
    0.85
     baj
    0.85
    enggar
    0.84
     Ojo
    0.84
    ߞ
    0.81
     Forks
    0.81
     selanjutnya
    0.80
    Activations Density 0.001%

    No Known Activations