© 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. 91720
    Prev
    Next
    INDEX
    Explanations

    connection strings or URLs

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

    The neuron activates on numeric literal tokens (digit sequences), e.g. port numbers, IP-style numbers, and other numeric constants in code or configuration.

    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
    นี้
    -0.76
     useCallback
    -0.75
    けれど
    -0.74
     zona
    -0.72
    áver
    -0.71
     About
    -0.69
     pernikahan
    -0.69
    讹
    -0.69
    一线
    -0.69
     axios
    -0.68
    POSITIVE LOGITS
    localhost
    2.38
     localhost
    2.03
    DESK
    0.96
    LAP
    0.95
    irc
    0.83
    ITAR
    0.81
     Мер
    0.78
     ört
    0.77
     lokal
    0.77
    LOCAL
    0.76
    Activations Density 0.042%

    No Known Activations