© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84452
    Prev
    Next
    INDEX
    Explanations

    Jordan and its region

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

    The neuron predominantly activates on mentions of “Jordan” (and related proper nouns, places, institutions, or people tied to Jordan).

    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
    _
    -1.52
    for
    -1.50
    i
    -1.46
    times
    -1.39
    n
    -1.38
    ógicos
    -1.35
    *
    -1.33
    \
    -1.27
     we
    -1.26
     jezt
    -1.24
    POSITIVE LOGITS
     discretion
    1.55
     сегодняш
    1.55
    ”),
    1.52
     precarious
    1.42
     hasty
    1.42
     nocturnal
    1.41
    喜んで
    1.40
    荐
    1.40
     añad
    1.40
    ”)
    1.40
    Activations Density 0.007%

    No Known Activations