© 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. 77517
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

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

    The neuron activates on SPDX license identifier markers (e.g., “SPDX -License”) in source‐code headers.

    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
     Readings
    -0.73
    EVENT
    -0.73
     internals
    -0.71
     endoc
    -0.69
    esse
    -0.68
    charging
    -0.66
     liga
    -0.66
    ждения
    -0.65
     Crossover
    -0.64
    gram
    -0.64
    POSITIVE LOGITS
    跡
    0.71
    طلاق
    0.66
     mecanismo
    0.65
     帝
    0.65
    알
    0.63
     chcete
    0.63
     Luxus
    0.63
     ngại
    0.63
    最高
    0.61
     Donovan
    0.61
    Activations Density 0.083%

    No Known Activations