© 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. 84406
    Prev
    Next
    INDEX
    Explanations

    words starting with pres

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

    The neuron activates on tokens beginning with the sequence “Pres,” effectively detecting words or prefixes starting with “Pres.”

    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
    ↵↵
    -2.78
     myriad
    -2.69
    も含
    -2.61
    .
    -2.56
    再去
    -2.56
     momentous
    -2.55
     única
    -2.42
     paltry
    -2.41
     verschieden
    -2.41
     podem
    -2.41
    POSITIVE LOGITS
     rajut
    2.64
    鏨
    2.52
     車場
    2.48
     rossa
    2.47
    Это
    2.47
    
    2.45
    Surprisingly
    2.41
    ⑧
    2.36
    vantaged
    2.34
    ೮
    2.33
    Activations Density 0.013%

    No Known Activations