© 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. 75067
    Prev
    Next
    INDEX
    Explanations

    debate, discussion forums

    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
    眛
    -2.45
     despicable
    -2.38
     všech
    -2.34
     teilen
    -2.34
     préparé
    -2.33
    Ꮞ
    -2.31
     fördern
    -2.30
     затем
    -2.30
    </h2>
    -2.28
    就直接
    -2.28
    POSITIVE LOGITS
    屺
    2.88
    涐
    2.66
    \
    2.42
     cok
    2.39
    🌻
    2.38
     uruguay
    2.38
     Singapur
    2.36
     kumar
    2.33
     ARAB
    2.30
     miy
    2.23
    Activations Density 0.006%

    No Known Activations