© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44222
    Prev
    Next
    INDEX
    Explanations

    Java graphics and image APIs

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

    The neuron is picking out programming‐library and class names (capitalized API identifiers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     juntamente
    -1.52
    );
    -1.52
     sentimentos
    -1.46
    Lire
    -1.37
     trás
    -1.36
     possu
    -1.36
     других
    -1.36
     usein
    -1.34
     doenças
    -1.34
     Vernunft
    -1.33
    POSITIVE LOGITS
    zeciw
    1.41
    りと
    1.41
     about
    1.41
    冽
    1.35
    5
    1.31
     trying
    1.30
     hacerle
    1.27
    isateurs
    1.26
     averiguar
    1.25
     Gegensatz
    1.24
    Activations Density 0.008%

    No Known Activations