© 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. 13705
    Prev
    Next
    INDEX
    Explanations

    posted by or changelog or news item

    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
     our
    -1.52
     in
    -1.41
     such
    -1.39
     without
    -1.25
     when
    -1.25
     السياس
    -1.24
     with
    -1.22
     so
    -1.20
    larımız
    -1.19
     each
    -1.18
    POSITIVE LOGITS
    TextEditing
    1.60
     قوات
    1.43
     braço
    1.41
     increíble
    1.40
     الشاشة
    1.38
    これは
    1.38
     この
    1.38
     patata
    1.37
     episódio
    1.37
    struktur
    1.36
    Activations Density 0.061%

    No Known Activations