© 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. 84817
    Prev
    Next
    INDEX
    Explanations

    closing or unpublishing

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

    The neuron flags programming‐style tokens and syntax markers (e.g. namespace separators "::", underscores, parentheses, numeric literals) in code.

    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
    乐观
    -0.96
     aktivieren
    -0.94
    assemblée
    -0.94
    Convolution
    -0.89
    attaque
    -0.87
    恻
    -0.87
     limité
    -0.87
     isolé
    -0.85
     purchase
    -0.85
     installing
    -0.85
    POSITIVE LOGITS
     goodbye
    1.63
     termination
    1.62
     farewell
    1.59
     exit
    1.55
     terminate
    1.44
     closing
    1.42
     terminating
    1.41
     Termination
    1.40
     Farewell
    1.40
     terminates
    1.39
    Activations Density 0.124%

    No Known Activations