© 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. 85673
    Prev
    Next
    INDEX
    Explanations

    words starting with uns

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

    The neuron responds to occurrences of words beginning with the prefix “uns.”

    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
    犼
    -2.91
     But
    -2.81
     แต่
    -2.75
    鞮
    -2.70
    
    -2.63
    鹋
    -2.59
    渽
    -2.42
    増えて
    -2.41
    孖
    -2.41
     eneste
    -2.34
    POSITIVE LOGITS
    狁
    2.98
    d
    2.83
    This
    2.75
    b
    2.72
    i
    2.52
    F
    2.50
    D
    2.47
    t
    2.42
    c
    2.41
    T
    2.41
    Activations Density 0.003%

    No Known Activations