© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101837
    Prev
    Next
    INDEX
    Explanations

    modal dialogue box

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

    the term "MessageBox" or variations of "box" in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on any instance of “box” in identifiers or UI component names (e.g. MessageBox, msg box, lightbox, dropbox).

    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
    x
    -2.91
    D
    -2.59
     当
    -2.59
     不
    -2.31
     получите
    -2.27
    ться
    -2.23
    }$,
    -2.22
     be
    -2.22
     「
    -2.20
    begin
    -2.16
    POSITIVE LOGITS
    .
    2.95
    <bos>
    2.75
     verſ
    2.58
    ቾ
    2.55
    酲
    2.52
    ጺ
    2.41
     unangemess
    2.39
    最后由
    2.38
     |]
    2.34
    给他们
    2.34
    Activations Density 0.002%

    No Known Activations