© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69921
    Prev
    Next
    INDEX
    Explanations

    deflate, inflater, and rights

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

    This neuron detects verbs ending in “-ate” (e.g., deflate, formulate).

    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
    Palabras
    -0.89
     kovo
    -0.88
     osoba
    -0.87
    tapkan
    -0.85
     швид
    -0.84
     nikt
    -0.84
    ienes
    -0.82
     Shrub
    -0.82
    rát
    -0.81
    ngoing
    -0.81
    POSITIVE LOGITS
     from
    0.82
     Dolly
    0.78
    бра
    0.77
     Sweden
    0.77
    Solicit
    0.75
     Norway
    0.73
    章节
    0.73
    ре
    0.72
     Ethio
    0.72
     suku
    0.72
    Activations Density 0.008%

    No Known Activations