© 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. 49436
    Prev
    Next
    INDEX
    Explanations

    enable Javascript

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

    The neuron lights up on snippets of code or configuration text—i.e. programming keywords, library/version identifiers, markup tokens, and other boilerplate seen in code examples.

    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
     Barça
    -0.81
    besar
    -0.75
     teach
    -0.75
    gante
    -0.73
     souri
    -0.72
    ContainsKey
    -0.71
    ENNIS
    -0.71
    aville
    -0.71
    日记
    -0.70
    黝
    -0.70
    POSITIVE LOGITS
    nth
    0.66
    weeper
    0.65
     performed
    0.64
    таж
    0.64
     lại
    0.63
     grand
    0.62
     המח
    0.62
     Grand
    0.61
    pou
    0.61
     population
    0.61
    Activations Density 0.066%

    No Known Activations