© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91988
    Prev
    Next
    INDEX
    Explanations

    code and documentation fragments

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

    The neuron fires primarily on numeric literals (e.g. version numbers, line numbers, numeric IDs) in code or config files.

    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
     homenaje
    -0.74
     presentaciones
    -0.71
    Uploader
    -0.71
     ansik
    -0.71
     normalerweise
    -0.69
     Raising
    -0.68
     Arkansas
    -0.68
    ěla
    -0.68
    血压
    -0.66
    ехали
    -0.66
    POSITIVE LOGITS
    ärme
    0.75
     Mocking
    0.71
    łów
    0.69
     grau
    0.68
    MONGO
    0.66
    циональный
    0.66
    dó
    0.66
     Çok
    0.65
    éndole
    0.65
     Chá
    0.64
    Activations Density 0.062%

    No Known Activations