© 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. 10-GEMMASCOPE-RES-131K
    7. 113380
    Prev
    Next
    INDEX
    Explanations

    internet protocol network communications

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

    the acronym "IP" (Internet Protocol) in technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the standalone acronym “IP” (Internet Protocol).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    vantaged
    -4.00
    '
    -3.89
    $
    -3.08
    öpfer
    -2.89
    s
    -2.88
    .
    -2.61
    A
    -2.61
    It
    -2.59
     —
    -2.58
    \
    -2.39
    POSITIVE LOGITS
    u
    3.09
    ㌧
    2.80
     शुर
    2.56
     Послед
    2.55
    zelfde
    2.42
    の使い方
    2.41
    鹟
    2.41
    𖥧
    2.39
    ו
    2.39
    樒
    2.38
    Activations Density 0.007%

    No Known Activations