© 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. 61266
    Prev
    Next
    INDEX
    Explanations

    snapshotting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    }$
    -2.78
    饜
    -2.72
    鲠
    -2.63
    ܆
    -2.56
     отличаются
    -2.55
    лением
    -2.48
    킁
    -2.47
     possu
    -2.45
     avec
    -2.44
    ⸰
    -2.44
    POSITIVE LOGITS
     να
    3.08
     Hundreds
    2.75
     untuk
    2.67
     dwindling
    2.66
    इटम
    2.63
    <bos>
    2.61
    ↵
    2.52
     excepcional
    2.45
    紧接着
    2.44
     để
    2.33
    Activations Density 0.002%

    No Known Activations