© 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. 41739
    Prev
    Next
    INDEX
    Explanations

    class/component declarations</div>

    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
    Наводи
    -1.26
     været
    -1.26
     vært
    -1.22
     или
    -1.16
     CERTAIN
    -1.13
     всичко
    -1.11
     Einfluß
    -1.09
     bestemt
    -1.09
    êtes
    -1.07
     sogenannte
    -1.06
    POSITIVE LOGITS
     for
    1.41
     at
    1.34
    sekten
    1.27
    たか
    1.22
     any
    1.19
     tidak
    1.15
     both
    1.09
     sonore
    1.09
    ਾਂ
    1.09
    Actress
    1.09
    Activations Density 0.047%

    No Known Activations