© 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. 22-GEMMASCOPE-RES-131K
    7. 79872
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

    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_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
     requer
    -1.28
     their
    -1.25
     or
    -1.11
     atau
    -1.10
     devient
    -1.05
     wajib
    -1.03
     junt
    -1.02
    机遇
    -1.02
    kontak
    -1.01
     ingredientes
    -1.00
    POSITIVE LOGITS
    ">{{$
    1.15
     deko
    1.13
     prenn
    1.09
     semelh
    1.06
     eyel
    1.05
    териал
    1.05
     kenzo
    1.05
     lidl
    1.05
     oock
    1.04
    と同じ
    1.02
    Activations Density 0.000%

    No Known Activations