© 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. 92783
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    This neuron fires on common boilerplate tokens—things like standard import/package names and repeated license‐header words—i.e. it’s detecting boilerplate 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_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
     Contribution
    -0.79
    Contribution
    -0.76
    ffekt
    -0.71
     تولد
    -0.69
    modo
    -0.69
    contribution
    -0.68
    Oi
    -0.67
     disobedience
    -0.67
     contributor
    -0.67
     оранже
    -0.67
    POSITIVE LOGITS
     Lighting
    0.80
    peza
    0.79
     lighting
    0.77
    र्
    0.75
    моро
    0.75
    斂
    0.71
    pagestyle
    0.67
     Ordnung
    0.67
    Fer
    0.66
     Fer
    0.65
    Activations Density 0.052%

    No Known Activations