© 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. 34-GEMMASCOPE-RES-131K
    7. 92142
    Prev
    Next
    INDEX
    Explanations

    starts with specific prefixes

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

    This neuron strongly activates on tokens containing repeated “y” characters (e.g. “YY,” “yy,” “yacc,” “yuitest,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    kic
    -0.94
     horno
    -0.87
     every
    -0.85
    catalyst
    -0.85
     dager
    -0.84
     with
    -0.83
     dipping
    -0.83
     escultura
    -0.79
     cesta
    -0.78
    whale
    -0.78
    POSITIVE LOGITS
     вашу
    0.89
    icano
    0.84
    
    0.79
     aimé
    0.78
     Gypsum
    0.78
    終
    0.77
    cb
    0.77
     atunci
    0.76
     Notepad
    0.76
    گرم
    0.76
    Activations Density 0.000%

    No Known Activations