© 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. 70327
    Prev
    Next
    INDEX
    Explanations

    medical and biological conditions

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

    section headers in academic or scientific papers.

    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_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
    9
    -3.25
    -
    -3.02
    8
    -2.67
    After
    -2.52
    6
    -2.50
    5
    -2.48
    3
    -2.45
    While
    -2.39
    Through
    -2.34
     После
    -2.34
    POSITIVE LOGITS
    ്ട
    2.80
    饧
    2.66
    ࿊
    2.61
    艽
    2.48
    ৄ
    2.45
    原神
    2.30
    诹
    2.30
    ￪
    2.28
    }
    2.27
    眚
    2.27
    Activations Density 0.045%

    No Known Activations