© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34840
    Prev
    Next
    INDEX
    Explanations

    Gael Guennebaud, Guilar

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

    The neuron fires strongest on fully qualified class or namespace references in code (i.e. sequences of CamelCase identifiers separated by backslashes).

    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
    rawdź
    -0.80
    ее
    -0.79
    }`
    -0.73
    endrait
    -0.73
    +='
    -0.72
     Winfrey
    -0.72
    ẳng
    -0.71
    KeyPair
    -0.70
    ULONG
    -0.69
    Източници
    -0.69
    POSITIVE LOGITS
     เน
    0.80
    wasi
    0.78
     sorta
    0.75
    ਜ਼
    0.75
     zrobi
    0.75
    がこの
    0.74
    事態
    0.73
    Boton
    0.73
    違反
    0.71
    ちな
    0.71
    Activations Density 0.057%

    No Known Activations