© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32343
    Prev
    Next
    INDEX
    Explanations

    XML tags and file paths

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

    The neuron fires on standalone punctuation tokens—especially periods and hyphens—common in code or CSS/HTML snippets.

    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
     оружи
    -0.81
    ::{
    -0.69
    ക്
    -0.67
    เวลา
    -0.67
    一代
    -0.66
    laubnis
    -0.66
     Pek
    -0.66
    olli
    -0.65
    UPI
    -0.65
    ี
    -0.64
    POSITIVE LOGITS
    منون
    0.68
    Público
    0.67
    iosk
    0.67
    rela
    0.66
     FUCK
    0.65
    relli
    0.65
    tamentos
    0.64
    EVP
    0.64
    łoni
    0.64
    andinavian
    0.63
    Activations Density 0.067%

    No Known Activations