© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73235
    Prev
    Next
    INDEX
    Explanations

    data transfer object

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

    The neuron activates on occurrences of the “DTO”/“Dto”/“dto” abbreviation (the data-transfer-object acronym).

    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
    that
    -3.53
     که
    -2.72
    沨
    -2.70
     That
    -2.53
    h
    -2.45
    潆
    -2.41
    那是
    -2.38
    ro
    -2.36
    *,
    -2.36
    では
    -2.34
    POSITIVE LOGITS
    _________
    2.66
    medriver
    2.61
    к
    2.55
    ⴽ
    2.55
    鉭
    2.52
     anún
    2.42
     créé
    2.34
     desblo
    2.33
     gratuito
    2.31
     Svizzera
    2.31
    Activations Density 0.003%

    No Known Activations