© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    from telemarketers

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

    The neuron activates on numeric sequences and punctuation that form IP addresses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    IP addresses and numerical identifiers in technical or web-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of IP addresses and related network/traffic details, especially explicit IPv4-style numeric addresses and discussions of tracking or logging them

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     installed
    0.56
     permangan
    0.54
     rhinestone
    0.53
     nitrog
    0.53
     antioxid
    0.53
     entra
    0.51
    ᱩ
    0.51
     Installed
    0.50
    тельность
    0.49
     चम्म
    0.49
    POSITIVE LOGITS
     IP
    1.20
    IP
    1.05
     IPs
    1.03
     ip
    0.95
     Ip
    0.89
    Ip
    0.85
    ip
    0.82
    IPV
    0.80
     आईपी
    0.77
    sourceIP
    0.77
    Activations Density 0.136%

    No Known Activations