© 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. 39401
    Prev
    Next
    INDEX
    Explanations

    prepositions of location and direction

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

    The neuron fires on instances of the verb “go” (and its inflected “goes”) and the adjoining prepositions “in” or “into,” i.e., phrases like “go into.”

    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
     Sweatshirt
    -1.63
     kaksi
    -1.58
     untuk
    -1.46
     oliveira
    -1.45
    their
    -1.42
     seguimos
    -1.41
    sweetalert
    -1.41
     dji
    -1.38
     fhall
    -1.36
     fras
    -1.36
    POSITIVE LOGITS
    ↵
    2.05
     Füße
    1.52
    </u>
    1.50
    Pf
    1.38
     in
    1.38
    ৄ
    1.33
    Галерея
    1.27
    紆
    1.20
     Pläne
    1.19
    もちろん
    1.17
    Activations Density 0.027%

    No Known Activations