© 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. 130847
    Prev
    Next
    INDEX
    Explanations

    image by or photo by

    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
     fof
    -1.39
    formatie
    -1.37
    ViewChild
    -1.34
    ἂ
    -1.31
    荦
    -1.29
    
    -1.29
    elernt
    -1.28
    岽
    -1.28
     também
    -1.28
     حالی
    -1.25
    POSITIVE LOGITS
     what
    1.64
     on
    1.60
    </h2>
    1.56
     one
    1.38
    хождение
    1.23
    </h5>
    1.21
    </h3>
    1.20
    ://
    1.16
    </em>
    1.16
    labas
    1.15
    Activations Density 0.027%

    No Known Activations