© 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. 22-GEMMASCOPE-RES-131K
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron is picking out code identifiers—names of functions, classes, threads, and similar tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     for
    -0.94
     or
    -0.88
     our
    -0.87
     whether
    -0.83
     another
    -0.82
     HttpHeaders
    -0.82
    código
    -0.81
     continues
    -0.81
     embracing
    -0.80
     famous
    -0.80
    POSITIVE LOGITS
     TÉ
    0.92
     bordo
    0.85
     ()=>
    0.82
    的技术
    0.80
     जान
    0.79
    тропо
    0.78
     दुनिया
    0.77
    川崎
    0.75
    不锈钢
    0.75
     Muddy
    0.75
    Activations Density 0.003%

    No Known Activations