© 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. 22-GEMMASCOPE-RES-131K
    4. 70756
    Prev
    Next
    INDEX
    Explanations

    counts total number

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

    The neuron detects words commonly found in code documentation or doc-comments (e.g. descriptive terms like “returning,” “length,” “for,” “its,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    werden
    -1.07
    Ș
    -0.89
    组合
    -0.86
    HttpClientModule
    -0.86
     golpea
    -0.85
    gène
    -0.84
    ributes
    -0.84
     kierunku
    -0.83
    UTES
    -0.83
     dólares
    -0.82
    POSITIVE LOGITS
     number
    1.55
     estimates
    1.32
     estimate
    1.27
     counting
    1.25
     total
    1.24
     count
    1.24
    的数量
    1.14
     تعداد
    1.13
    getNumberOf
    1.12
    NumberOf
    1.09
    Activations Density 0.023%

    No Known Activations