© 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. 34-GEMMASCOPE-RES-131K
    7. 55634
    Prev
    Next
    INDEX
    Explanations

    external and outside

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

    The neuron strongly activates on prepositions and verbs that describe directional transfer or flow in technical descriptions (e.g. “via,” “through,” “to”)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    SneakyThrows
    -0.93
    參考文獻
    -0.80
    żenia
    -0.73
    ଏ
    -0.68
     samtidigt
    -0.67
    Примітки
    -0.66
    回去
    -0.66
    inee
    -0.65
    ("/{
    -0.64
    cula
    -0.63
    POSITIVE LOGITS
     external
    6.94
     outside
    6.31
    external
    5.59
     External
    5.13
    External
    5.03
     exterior
    5.00
    外部
    4.97
    EXTERNAL
    4.78
     внеш
    4.75
     externally
    4.75
    Activations Density 0.368%

    No Known Activations