© 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. 10-GEMMASCOPE-RES-131K
    7. 129936
    Prev
    Next
    INDEX
    Explanations

    in: country name

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

    The neuron fires when it sees the preposition “in” immediately introducing a numeric value (e.g. “in 116,” “in 128,” etc.).

    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
     a
    -1.93
     involve
    -1.60
     imagined
    -1.52
    迺
    -1.51
     something
    -1.49
     involved
    -1.41
     vytvoř
    -1.39
     what
    -1.38
     contado
    -1.34
     また
    -1.30
    POSITIVE LOGITS
     otros
    1.63
    3
    1.60
    ediakan
    1.55
     комнату
    1.48
     diğer
    1.46
    vät
    1.45
     mimpi
    1.40
     otras
    1.40
    TKey
    1.38
     jeszcze
    1.37
    Activations Density 0.115%

    No Known Activations