© 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. 60587
    Prev
    Next
    INDEX
    Explanations

    module.identifier

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

    This neuron detects occurrences of module, library, or package identifiers (e.g. in import/include/namespace or registration statements).

    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
     later
    -1.13
     latter
    -1.05
     why
    -1.05
     quick
    -0.99
     first
    -0.98
     J
    -0.91
     Probably
    -0.91
     Similar
    -0.89
    点评
    -0.88
     Since
    -0.87
    POSITIVE LOGITS
     pérd
    1.16
     Boba
    1.07
     Sweatshirt
    1.05
     exprimer
    1.03
    Bah
    1.02
     mijne
    1.02
     trône
    1.01
     tredje
    1.00
    wände
    0.98
     severa
    0.98
    Activations Density 0.033%

    No Known Activations