© 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. 10-GEMMASCOPE-RES-131K
    4. 85113
    Prev
    Next
    INDEX
    Explanations

    Northern, Southern, Eastern, Second, Fourth

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

    The neuron fires on directional and ordinal qualifiers (e.g. “North,” “Northwest,” “Eastern,” “Second,” “Fourth,” “Sixth”) used in place names or administrative divisions.

    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
    .
    -1.76
     empfohlen
    -1.39
    getLatitude
    -1.38
     merkwür
    -1.37
     üblichen
    -1.30
     traditionellen
    -1.28
     susun
    -1.28
    我对
    -1.27
    ᝢ
    -1.26
    días
    -1.22
    POSITIVE LOGITS
     of
    1.48
    of
    1.47
    "},
    1.41
    ")
    1.38
     seiner
    1.36
    !",
    1.35
    o
    1.34
    </td>
    1.30
    tikel
    1.27
     incluso
    1.27
    Activations Density 0.108%

    No Known Activations