© 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. 32984
    Prev
    Next
    INDEX
    Explanations

    names ending in yn

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

    The neuron fires on tokens containing the letter sequence “yn.”

    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
     dormit
    -0.81
     привод
    -0.79
     [{
    
    -0.78
    いただきたい
    -0.74
    र्ड
    -0.73
     competição
    -0.73
    ון
    -0.73
     আর
    -0.72
     esquecer
    -0.71
    يب
    -0.71
    POSITIVE LOGITS
    cannot
    0.88
    finite
    0.82
     resume
    0.81
    aned
    0.79
     calon
    0.78
    pys
    0.78
     seminar
    0.78
     Johan
    0.77
     laiton
    0.77
    ancial
    0.76
    Activations Density 0.036%

    No Known Activations