© 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. 58558
    Prev
    Next
    INDEX
    Explanations

    http urls

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

    The neuron strongly lights up on tokens that begin URLs (e.g. “http”) and other long punctuation–heavy markers (like lines of “*”), i.e. it flags URL and decorative separator tokens.

    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
    OrderItem
    -0.73
    lama
    -0.69
    Transcripción
    -0.68
    diagnostics
    -0.68
    땡
    -0.68
    Grup
    -0.67
    Abdullah
    -0.65
     Grup
    -0.65
     योग
    -0.65
    舞台
    -0.65
    POSITIVE LOGITS
    ventude
    0.82
     Ashton
    0.79
    यह
    0.70
    趋
    0.70
     slä
    0.68
     реда
    0.68
     GLE
    0.68
     meilleure
    0.68
    鸢
    0.66
     impul
    0.66
    Activations Density 0.026%

    No Known Activations