© 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. 22-GEMMASCOPE-RES-131K
    4. 313
    Prev
    Next
    INDEX
    Explanations

    scientific names in parentheses

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

    year citations in scientific taxonomic entries, particularly those from the 19th and early 20th centuries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    だからこそ
    -0.94
     P
    -0.91
     释放
    -0.88
     Just
    -0.87
     da
    -0.87
     zwięks
    -0.87
    控え
    -0.87
     prepare
    -0.86
     system
    -0.86
     said
    -0.85
    POSITIVE LOGITS
     poliuret
    1.23
     vêtement
    1.20
     dekoratif
    1.13
     kalori
    1.13
     keramik
    1.12
     uova
    1.09
    tempat
    1.09
     vider
    1.08
     karet
    1.06
     kuah
    1.06
    Activations Density 0.013%

    No Known Activations