© 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. 34-GEMMASCOPE-RES-131K
    7. 37793
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    The neuron fires on all‐caps or mixed‐caps identifier fragments in code (e.g. constant names, class or variable name parts).

    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
     there
    -1.00
     and
    -0.97
    As
    -0.96
    Being
    -0.95
    There
    -0.94
    Another
    -0.93
     supaya
    -0.89
     milyen
    -0.87
    </em>
    -0.87
     的
    -0.86
    POSITIVE LOGITS
    itys
    1.04
     effici
    1.03
     italiens
    1.03
    鲥
    1.02
     tragedia
    1.02
    ครื่อง
    1.02
     desinf
    1.02
    SYLLABLE
    1.01
     cristal
    1.01
     promet
    1.00
    Activations Density 0.111%

    No Known Activations