© 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. 26452
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

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

    The neuron strongly lights up on past-tense verb forms (words ending in “-ed”).

    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
     stratég
    -1.35
     lourdes
    -1.34
     cuchillo
    -1.28
     escote
    -1.27
     étr
    -1.26
     bancaria
    -1.26
     kompati
    -1.25
     yyb
    -1.23
     metálica
    -1.22
    Figli
    -1.21
    POSITIVE LOGITS
     to
    1.32
    祗
    1.02
     altercation
    1.02
     underdog
    0.96
     S
    0.94
     những
    0.91
     prodigy
    0.91
     gingerbread
    0.91
     rookies
    0.91
    al
    0.90
    Activations Density 0.000%

    No Known Activations