© 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. 123528
    Prev
    Next
    INDEX
    Explanations

    variable names and assignments

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

    variable assignments in Python code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    quite
    -2.14
     astounding
    -2.09
    extremely
    -2.05
    只是一
    -1.92
    generally
    -1.92
     WIL
    -1.92
     opulent
    -1.91
     VERY
    -1.91
    菒
    -1.85
    possibly
    -1.84
    POSITIVE LOGITS
     any
    2.05
     ostensibly
    2.00
     undoubtedly
    1.95
     haphazard
    1.91
     one
    1.91
     arguably
    1.90
    After
    1.89
    Before
    1.89
    Several
    1.88
     should
    1.86
    Activations Density 0.029%

    No Known Activations