© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65365
    Prev
    Next
    INDEX
    Explanations

    status, size, Post, Refer, GROUP

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

    The neuron fires on programming‐style identifiers and constants (e.g. JSON keys, class/enum names, camel- or Pascal-case 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_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
    lamabad
    -1.65
     hinzufügen
    -1.63
    reasonably
    -1.59
    albeit
    -1.55
     pią
    -1.54
     Američ
    -1.53
     pedras
    -1.53
     ocasi
    -1.51
     الجلد
    -1.51
     Vgl
    -1.49
    POSITIVE LOGITS
     so
    1.96
     overall
    1.88
     is
    1.59
    1
    1.55
     reduced
    1.52
    ַּ
    1.51
     or
    1.49
    おわりに
    1.45
    ulfon
    1.45
    em
    1.43
    Activations Density 0.006%

    No Known Activations