© 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. 99740
    Prev
    Next
    INDEX
    Explanations

    new def, require, render

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

    The neuron fires on the punctuation and operator tokens that make up Ruby code syntax (e.g. ., :, =>, {, }, |, <, etc.).

    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
     curated
    -1.05
     Brexit
    -0.92
     Zika
    -0.89
     cybersecurity
    -0.88
     emoji
    -0.88
     Trump
    -0.85
     GDPR
    -0.83
    iteiten
    -0.82
     emojis
    -0.80
    Brexit
    -0.79
    POSITIVE LOGITS
     {:
    1.08
    {:
    0.91
     Encounter
    0.81
     MySpace
    0.80
     MiG
    0.79
     XHTML
    0.78
    公会
    0.78
     iPod
    0.77
     concentrates
    0.76
     Blanket
    0.74
    Activations Density 0.127%

    No Known Activations