© 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. 34-GEMMASCOPE-RES-131K
    4. 82563
    Prev
    Next
    INDEX
    Explanations

    unless required by applicable law

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

    The neuron detects occurrences of the word “Unless” (as in the start of license-condition boilerplate).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ResponseBody
    -0.74
    dera
    -0.73
    heim
    -0.73
    hr
    -0.72
    bosch
    -0.71
     Пи
    -0.70
     Set
    -0.69
    答
    -0.69
     Пла
    -0.68
    edc
    -0.68
    POSITIVE LOGITS
     Brahms
    0.73
     Handels
    0.73
    Docker
    0.72
    烁
    0.71
     diser
    0.69
    Première
    0.68
     Acqua
    0.68
    Tipp
    0.68
    loginForm
    0.67
    ✳
    0.67
    Activations Density 0.087%

    No Known Activations