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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103712
    Prev
    Next
    INDEX
    Explanations

    Android Open Source Project

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

    The neuron is triggered by tokens that occur in URLs and other code‐style link or path syntax (e.g. “http,” “://,” domain names, and slash-delimited paths”).

    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
     administ
    -0.78
    ICKS
    -0.77
     Dimensions
    -0.75
     depende
    -0.75
     capita
    -0.75
     юби
    -0.75
    ⇲
    -0.72
    デニム
    -0.71
     Scientific
    -0.70
     identific
    -0.70
    POSITIVE LOGITS
     Android
    1.88
     Google
    1.84
    Google
    1.67
    Android
    1.52
     android
    1.48
    GOOGLE
    1.40
    android
    1.38
     google
    1.29
     GOOGLE
    1.24
    google
    1.22
    Activations Density 0.201%

    No Known Activations