© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73877
    Prev
    Next
    INDEX
    Explanations

    cloud, open source, data management, virtual machines

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

    The neuron fires on documentation-style definitional sentences—especially those that introduce or define a technical service or API.

    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
     totally
    -1.21
     only
    -1.20
     in
    -1.17
     !!
    -1.13
     utterly
    -1.12
     three
    -1.12
     at
    -1.12
     ONLY
    -1.11
     expertly
    -1.09
     overtly
    -1.09
    POSITIVE LOGITS
     faciliter
    1.45
     Dinas
    1.34
    iiiiiiii
    1.23
     lauded
    1.21
    ___________
    1.17
    -------
    
    1.15
     semelh
    1.13
    ~)
    1.13
     ſec
    1.13
     alluring
    1.13
    Activations Density 0.181%

    No Known Activations