© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111789
    Prev
    Next
    INDEX
    Explanations

    words beginning with Dy

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

    The neuron fires specifically on tokens that begin with “Dy” followed immediately by digits (e.g. “Dy206,” “Dy196,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ܜ
    -3.42
    镚
    -2.98
    ⑊
    -2.84
    鲵
    -2.77
    ンダム
    -2.73
    
    -2.64
    ről
    -2.63
    𓁹
    -2.61
    歘
    -2.59
    徧
    -2.58
    POSITIVE LOGITS
    *
    2.84
    Our
    2.81
     οποίο
    2.48
     brownish
    2.36
    Your
    2.30
    All
    2.30
    a
    2.27
    牁
    2.27
    Three
    2.23
    Ꮄ
    2.23
    Activations Density 0.004%

    No Known Activations