© 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. 38446
    Prev
    Next
    INDEX
    Explanations

    start of common phrases

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

    The neuron selectively activates on numeric decade references (e.g. “1970s”).

    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
    anciers
    -0.75
    halen
    -0.73
     doch
    -0.73
     CEA
    -0.71
     LS
    -0.71
    眼前
    -0.70
     дете
    -0.70
     musi
    -0.70
     HD
    -0.69
    enein
    -0.69
    POSITIVE LOGITS
    ispo
    0.86
    Phong
    0.85
     Throm
    0.80
    原來
    0.80
     topsoil
    0.79
    qiao
    0.78
    =""></
    0.77
     mathematicians
    0.76
     conges
    0.76
     isole
    0.76
    Activations Density 0.000%

    No Known Activations