© 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. 10482
    Prev
    Next
    INDEX
    Explanations

    Assume or suppose

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

    The neuron fires on the usual mathematical “assumption” markers (words like “Suppose” and “Assume”) that introduce hypotheses or setup in formal statements.

    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
    憷
    -1.67
     rozs
    -1.66
     ewigen
    -1.61
     berühmten
    -1.60
     ogrom
    -1.60
     través
    -1.57
     koncep
    -1.54
    zbęd
    -1.51
     rompecabezas
    -1.51
     celos
    -1.48
    POSITIVE LOGITS
    Since
    1.61
     vist
    1.38
     abit
    1.38
     ankara
    1.36
    之一
    1.35
     toni
    1.35
     taylor
    1.34
     設備
    1.34
     memutus
    1.30
     sucks
    1.29
    Activations Density 0.014%

    No Known Activations