© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25715
    Prev
    Next
    INDEX
    Explanations

    whether or not

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

    This neuron fires on words in contrastive or comparative constructions (e.g. in “not … but …,” “better than …,” “not only …,” “whether or not …”).

    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
    ebly
    -1.09
     nonchal
    -1.07
     oczywiście
    -1.05
    Poder
    -1.04
     وتح
    -0.98
     таких
    -0.98
    athered
    -0.96
    STILL
    -0.96
     développer
    -0.95
    combined
    -0.94
    POSITIVE LOGITS
     as
    0.95
    isPresent
    0.93
    የ
    0.93
     seeks
    0.93
     Jahrhunderts
    0.92
     zufolge
    0.91
     for
    0.90
     cristiana
    0.87
     spurred
    0.87
     kurikulum
    0.85
    Activations Density 0.037%

    No Known Activations