© 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. 66792
    Prev
    Next
    INDEX
    Explanations

    Takumi, Shumaker, O'Mara, Tsurumi

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

    The neuron is looking for the character sequence “uma” within tokens.

    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
    "}
    -2.77
    )$
    -2.77
    ０
    -2.55
     {
    -2.50
    It
    -2.48
     Out
    -2.47
    \
    -2.42
    ");
    -2.39
    "+
    -2.39
    "...
    -2.38
    POSITIVE LOGITS
    𓆜
    2.39
     groter
    2.39
    を経
    2.34
    并将
    2.31
    蚨
    2.22
    鮰
    2.20
    鸵
    2.19
    
    2.19
    呓
    2.14
    média
    2.06
    Activations Density 0.023%

    No Known Activations