© 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. 22-GEMMASCOPE-RES-131K
    7. 67404
    Prev
    Next
    INDEX
    Explanations

    assumptions and premises

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

    The neuron detects discourse markers that introduce or assert assumptions and premises (e.g. words like “assume,” “assumption,” “premise,” “conceding,” “for granted,” and similar logical‐argument connectors).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    zeption
    -0.91
    iddhartha
    -0.90
    edoria
    -0.86
     шанс
    -0.86
     despite
    -0.85
    箐
    -0.84
    iconductor
    -0.82
     רג
    -0.82
    Politik
    -0.82
    เวลา
    -0.82
    POSITIVE LOGITS
     premise
    1.46
     assumption
    1.34
     assumed
    1.21
     assumptions
    1.13
     baseline
    1.11
    前提
    1.05
    assumed
    1.05
     asume
    1.04
     established
    1.02
    assume
    1.02
    Activations Density 0.065%

    No Known Activations