© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    programming libraries and mathematics

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

    references to scientific or technical libraries and frameworks, particularly in mathematical or data science contexts.

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

    The neuron fires strongly on tokens that look like programming library, module, or package names (e.g. “math,” “asio,” “PyMC,” “Boost Units,” 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_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
    s
    -1.41
    pezifische
    -1.30
    händler
    -1.24
     Indien
    -1.21
     poř
    -1.19
     órganos
    -1.19
     zpra
    -1.18
    ungsbedingungen
    -1.16
    ouchable
    -1.16
    dos
    -1.13
    POSITIVE LOGITS
                    
    1.62
     then
    1.43
     ftate
    1.36
     augusti
    1.35
    ℝ
    1.32
                       
    1.31
    目标
    1.28
    voje
    1.27
     también
    1.26
    Ingrédients
    1.26
    Activations Density 0.013%

    No Known Activations