© 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. 10-GEMMASCOPE-RES-131K
    7. 110557
    Prev
    Next
    INDEX
    Explanations

    under context

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

    The neuron specifically responds to occurrences of the word “Under.”

    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
    B
    -2.58
    V
    -2.52
    d
    -2.42
    b
    -2.30
    S
    -2.27
    W
    -2.25
    M
    -2.23
    F
    -2.23
    R
    -2.23
    as
    -2.23
    POSITIVE LOGITS
     Conſ
    2.56
     Inſ
    2.45
    ⎆
    2.44
     Reſ
    2.41
     После
    2.25
    Vous
    2.17
    瞜
    2.17
    媄
    2.16
     coveted
    2.14
    饜
    2.14
    Activations Density 0.019%

    No Known Activations