© 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. 54296
    Prev
    Next
    INDEX
    Explanations

    citing research or proper names

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

    The neuron fires specifically on the standalone uppercase letter “R” token (as used in reference or content codes).

    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
     your
    -1.36
    ++;
    -1.21
     Genuss
    -1.14
    ätta
    -1.13
     hilft
    -1.13
     secondo
    -1.11
    ียญ
    -1.11
    (){
    -1.10
     peut
    -1.06
    Библи
    -1.05
    POSITIVE LOGITS
     cinquième
    1.30
     Pary
    1.13
     rower
    1.09
    ,
    1.07
     splitter
    1.07
    äft
    1.04
    licy
    1.02
    孃
    1.01
    SSS
    1.00
     Ws
    1.00
    Activations Density 0.000%

    No Known Activations