© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75259
    Prev
    Next
    INDEX
    Explanations

    licensed under

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

    The neuron responds to the preposition “under” (and its Czech equivalent “pod”).

    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
     verhind
    -2.48
     behandel
    -2.30
     bedien
    -2.30
    珰
    -2.30
     considérons
    -2.22
     sowieso
    -2.19
    也会
    -2.08
    gucig
    -2.08
    bereitung
    -2.05
     persegu
    -2.05
    POSITIVE LOGITS
    It
    2.89
    偌
    2.58
     sechs
    2.53
     übri
    2.41
     Erlebn
    2.34
     eigentliche
    2.28
     體
    2.22
     nella
    2.22
     Veränder
    2.19
     bestätigen
    2.17
    Activations Density 0.009%

    No Known Activations