© 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. 81322
    Prev
    Next
    INDEX
    Explanations

    Filipino films

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

    The neuron responds primarily to uncommon or named‐entity tokens—especially proper names, foreign‐language words, and numeric figures—rather than to ordinary English words.

    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
     Aye
    -0.81
    pruch
    -0.79
    dej
    -0.78
    MING
    -0.78
    рения
    -0.77
    dings
    -0.77
    ymm
    -0.77
    Frank
    -0.76
     UIButton
    -0.76
     Scholar
    -0.76
    POSITIVE LOGITS
    Jimin
    0.76
    Nio
    0.74
    emporio
    0.68
    adesivo
    0.67
    autorisation
    0.66
     consente
    0.66
    rq
    0.66
    comprar
    0.65
    气氛
    0.65
    ukin
    0.64
    Activations Density 0.025%

    No Known Activations